This survey provides an in-depth analysis of knowledge conflicts for large language models (LLMs), highlighting the complex challenges they encounter when blending contextual and parametric knowledge. Our focus is on three categories of knowledge conflicts: context-memory, inter-context, and intra-memory conflict. These conflicts can significantly impact the trustworthiness and performance of LLMs, especially in real-world applications where noise and misinformation are common. By categorizing these conflicts, exploring the causes, examining the behaviors of LLMs under such conflicts, and reviewing available solutions, this survey aims to shed light on strategies for improving the robustness of LLMs, thereby serving as a valuable resource for advancing research in this evolving area.

Progress in Text-to-Image (T2I) models has significantly advanced the generation of images from textual descriptions. Existing metrics, such as CLIP, effectively measure the semantic alignment between single prompts and their corresponding images. However, they fall short in evaluating a model’s ability to generalize across a broad spectrum of textual inputs. To address this gap, we propose the VLEU (Visual Language Evaluation Understudy) metric. VLEU leverages the power of Large Language Models (LLMs) to sample from the visual text domain, encompassing the entire range of potential inputs for the T2I task, to generate a wide variety of visual text. The images generated by T2I models from these prompts are then assessed for their alignment with the input text using the CLIP model. VLEU quantitatively measures a model’s generalizability by computing the Kullback-Leibler (KL) divergence between the visual text marginal distribution and the conditional distribution over the images generated by the model. This provides a comprehensive metric for comparing the overall generalizability of T2I models, beyond single-prompt evaluations, and offers valuable insights during the finetuning process. Our experimental results demonstrate VLEU’s effectiveness in evaluating the generalizability of various T2I models, positioning it as an essential metric for future research and development in image synthesis from text prompts. Our code and data will be publicly available at https://github.com/mio7690/VLEU.

Large Language Models (LLMs) can interact with the real world by connecting with versatile external APIs, resulting in better problem-solving and task automation capabilities. Previous research primarily either focuses on APIs with limited arguments from a single source or overlooks the complex dependency relationship between different APIs. However, it is essential to utilize multiple APIs collaboratively from various sources, especially for complex user instructions. In this paper, we introduce MetaBench, the first benchmark to evaluate LLMs’ ability to plan and execute multiple APIs from various sources in order to complete the user’s task. Specifically, we consider two significant challenges in multiple APIs: 1) graph structures: some APIs can be executed independently while others need to be executed one by one, resulting in graph-like execution order; and 2) permission constraints: which source is authorized to execute the API call. We have experimental results on 9 distinct LLMs; e.g., GPT-4o achieves only a 2.0% success rate at the most complex instruction, revealing that the existing state-of-the-art LLMs still cannot perform well in this situation even with the help of in-context learning and finetuning. Our code and data are publicly available at https://github.com/ruleGreen/AppBench.

The growing interest in Large Language Models (LLMs) for specialized applications has revealed a significant challenge: when tailored to specific domains, LLMs tend to experience catastrophic forgetting, compromising their general capabilities and leading to a suboptimal user experience. Additionally, crafting a versatile model for multiple domains simultaneously often results in a decline in overall performance due to confusion between domains. In response to these issues, we present the RolE Prompting Guided Multi-Domain Adaptation (REGA) strategy. This novel approach effectively manages multi-domain LLM adaptation through three key components: 1) Self-Distillation constructs and replays general-domain exemplars to alleviate catastrophic forgetting. 2) Role Prompting assigns a central prompt to the general domain and a unique role prompt to each specific domain to minimize inter-domain confusion during training. 3) Role Integration reuses and integrates a small portion of domain-specific data to the general-domain data, which are trained under the guidance of the central prompt. The central prompt is used for a streamlined inference process, removing the necessity to switch prompts for different domains.Empirical results demonstrate that REGA effectively alleviates catastrophic forgetting and inter-domain confusion. This leads to improved domain-specific performance compared to standard fine-tuned models, while still preserving robust general capabilities.

The success of large language models (LLM) benefits from large-scale model parameters and large amounts of pre-training data. However, the textual data for training LLM can not be confirmed to be legal because they are crawled from different web sites. For example, there are copyrighted articles, personal reviews and information in the pre-training data for LLM which are illegal. To address the above issue and develop legal LLM, we propose to detect the pre-training data from LLM in a pure black-box way because the existing LLM services only return the generated text. The previous most related works are the membership inference attack (MIA) on machine learning models to detect the training data from them. But the existing methods are based on analyzing the output probabilities of models which are unrealistic to LLM services. To tackle the problem, we firstly construct the benchmark datasets by collecting textual data from different domains as the seen and unseen pre-training data for LLMs. Then, we investigate a black-box framework named DPDLLM, with the only access to the generated texts from LLM for detecting textual data whether was used to train it. In the proposed framework, we exploit GPT-2 as the reference model to fit the textual data and feed the generated text from LLM into it to acquire sequence probabilities as the significant feature for detection. The experimental results on the benchmark datasets demonstrate that DPDLLM is effective on different popular LLMs and outperforms the existing methods.

This paper surveys and organizes research works of medical dialog systems, which is an important yet challenging task. Although these systems have been surveyed in the medical community from an application perspective, a systematic review from a rigorous technical perspective has to date remained noticeably absent. As a result, an overview of the categories, methods, evaluation of medical dialogue systems remain limited and underspecified, hindering the further improvement of this area. To fill this gap, we investigate an initial pool of 325 papers from well-known computer science, natural language processing conferences and journals, and make an overview. Recently, large language models have shown strong model capacity on downstream tasks, which also reshape medical dialog systems’ foundation.Despite the alluring practical application value, current medical dialogue systems still suffer from problems. To this end, this paper lists grand challenges of medical dialog systems, especially of large language models.

Large Language Models (LLMs) have shown great potential in the biomedical domain with the advancement of retrieval-augmented generation (RAG). However, existing retrieval-augmented approaches face challenges in addressing diverse queries and documents, particularly for medical knowledge queries, resulting in sub-optimal performance. To address these limitations, we propose a novel plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search (SeRTS) based on Monte Carlo Tree Search (MCTS) and a self-rewarding paradigm. By combining the reasoning capabilities of LLMs with the effectiveness of tree search, SeRTS boosts the zero-shot performance of retrieving high-quality and informative results for RAG. We further enhance retrieval performance by fine-tuning LLMs with Proximal Policy Optimization (PPO) objectives using the trajectories collected by SeRTS as feedback. Controlled experiments using the BioASQ-QA dataset with GPT-3.5-Turbo and LLama2-7b demonstrate that our method significantly improves the performance of the BM25 retriever and surpasses the strong baseline of self-reflection in both efficiency and scalability. Moreover, SeRTS generates higher-quality feedback for PPO training than self-reflection. Our proposed method effectively adapts LLMs to document retrieval tasks, enhancing their ability to retrieve highly relevant documents for RAG in the context of medical knowledge queries. This work presents a significant step forward in leveraging LLMs for accurate and comprehensive biomedical question answering.

Retrieval-Augmented Generation (RAG) is widely used to inject external non-parametric knowledge into large language models (LLMs). Recent works suggest that Knowledge Graphs (KGs) contain valuable external knowledge for LLMs. Retrieving information from KGs differs from extracting it from document sets. Most existing approaches seek to directly retrieve relevant subgraphs, thereby eliminating the need for extensive SPARQL annotations, traditionally required by semantic parsing methods. In this paper, we model the subgraph retrieval task as a conditional generation task handled by small language models. Specifically, we define a subgraph identifier as a sequence of relations, each represented as a special token stored in the language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, achieves competitive retrieval performance compared to state-of-the-art models relying on 7B parameters, demonstrating that small language models are capable of performing the subgraph retrieval task. Furthermore, our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks. Our model and data will be made available online: https://github.com/hwy9855/GSR.

With the increasing risk posed by jailbreak attacks, recent studies have investigated various methods to improve the safety of large language models (LLMs), mainly falling into two strategies: safety training and safeguards. Safety training involves fine-tuning the LLM with adversarial samples, which activate the LLM’s capabilities against jailbreak. However, it is not always effective in countering new attacks and often leads to potential performance degradation. Safeguards, on the other hand, are methods using additional models to filter harmful content from the LLM’s response. Nevertheless, they can only reduce a limited amount of harmful output and introduce extra computational costs. Given the distinct strengths and weaknesses of both, we combine them to balance out their flaws and propose a more effective method called Self-Guard.Specifically, we train the LLM to review its responses for any harmful content and append a [harmful] or [harmless] tag to the end of the response. In this way, Self-Guard possesses the advantages of safety training, leveraging the powerful capabilities of the LLMs themselves to detect harmfulness. Besides that, it gains flexibility like safeguards, making the safety check target the output side, which makes the system less vulnerable to attack updates. Experimental results indicate that our Self-Guard can effectively defend against jailbreak attacks and will not cause LLMs’ performance degradation.

Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful.Nevertheless, some human instructions are often malicious or misleading and following them will lead to untruthful and unsafe responses.Previous work rarely focused on understanding how LLMs manage instructions based on counterfactual premises, referred to here as inductive instructions, which may stem from users’ false beliefs or malicious intents.In this paper, we aim to reveal the behaviors of LLMs towards inductive instructions and enhance their truthfulness and helpfulness accordingly. Specifically, we first introduce a benchmark of Inductive Instructions (INDust), where the false knowledge is incorporated into instructions in multiple different styles. After extensive human and automatic evaluations, we uncovered a universal vulnerability among LLMs in processing inductive instructions.Additionally, we identified that different inductive styles affect the models’ ability to identify the same underlying errors,and the complexity of the underlying assumptions also influences the model’s performance.Motivated by these results, we propose Dual-critique prompting to improve LLM robustness against inductive instructions.Our experiments demonstrate that Dual-critique prompting significantly bolsters the robustness of a diverse array of LLMs, even when confronted with varying degrees of inductive instruction complexity and differing inductive styles.

Prompting is an alternative approach for utilizing pre-trained language models (PLMs) in classification tasks. In contrast to fine-tuning, prompting is more understandable for humans because it utilizes natural language to interact with the PLM, but it often falls short in terms of accuracy. While current research primarily focuses on enhancing the performance of prompting methods to compete with fine-tuning, we believe that these two approaches are not mutually exclusive, each having its strengths and weaknesses. In our study, we depart from the competitive view of prompting versus fine-tuning and instead combine them, introducing a novel method called F&P. This approach enables us to harness the advantages of Fine-tuning for accuracy and the explainability of Prompting simultaneously. Specifically, we reformulate the sample into a prompt and subsequently fine-tune a linear classifier on top of the PLM. Following this, we extract verbalizers according to the weight of this classifier. During the inference phase, we reformulate the sample in the same way and query the PLM. The PLM generates a word, which is then subject to a dictionary lookup by the verbalizer to obtain the prediction. Experiments show that keeping only 30 keywords for each class can achieve comparable performance as fine-tuning. On the other hand, both the prompt and verbalizers are constructed in natural language, making them fully understandable to humans. Hence, the F&P method offers an effective and transparent way to employ a PLM for classification tasks.

In conversational AI, effectively employing long-term memory improves personalized and consistent response generation. Existing work only concentrated on a single type of long-term memory, such as preferences, dialogue history, or social relationships, overlooking their interaction in real-world contexts. To this end, inspired by the concept of semantic memory and episodic memory from cognitive psychology, we create a new and more comprehensive Chinese dataset, coined as PerLTQA, in which world knowledge, profiles, social relationships, events, and dialogues are considered to leverage the interaction between different types of long-term memory for question answering (QA) in conversation. Further, based on PerLTQA, we propose a novel framework for memory integration in QA, consisting of three subtasks: Memory Classification, Memory Retrieval, and Memory Fusion, which provides a comprehensive paradigm for memory modeling, enabling consistent and personalized memory utilization. This essentially allows the exploitation of more accurate memory information for better responses in QA. We evaluate this framework using five LLMs and three retrievers. Experimental results demonstrate the importance of personal long-term memory in the QA task

Dialogue policy learning (DPL) aims to determine an abstract representation (also known as action) to guide what the response should be. Typically, DPL is cast as a sequential decision problem across a series of predefined action candidates. However, such static and narrow actions can limit response diversity and impede the dialogue agent’s adaptability to new scenarios and edge cases. To overcome these challenges, we introduce a novel Joint Transformer Reinforcement Learning framework, coined as JoTR, where a text-to-text Transformer-based model is employed to directly generate dialogue actions. More concretely, JoTR formulates a token-grained policy, facilitating more dynamic and adaptable dialogue action generation without the need for predefined action candidates. This method not only enhances the diversity of responses but also significantly improves the system’s capability to manage unfamiliar scenarios. Furthermore, JoTR utilizes Reinforcement Learning with a reward-shaping mechanism to efficiently fine-tune the token-grained policy. This allows the model to evolve through interactions, thereby enhancing its performance over time. Our extensive evaluation demonstrates that JoTR surpasses previous state-of-the-art models, showing improvements of 9% and 13% in success rate, and 34% and 37% in the diversity of dialogue actions across two benchmark dialogue modeling tasks respectively. These results have been validated by both user simulators and human evaluators. Code and data are available at ://github.com/KwanWaiChung/JoTR.

Multimodal information extraction (MIE) is a challenging task which aims to extract the structural information in free text coupled with the image for constructing the multimodal knowledge graph. The entity-based MIE tasks are based on the entity information to complete the specific tasks. However, the existing methods only investigated the entity-based MIE tasks under supervised learning with adequate labeled data. In the real-world scenario, collecting enough data and annotating the entity-based samples are time-consuming, and impractical. Therefore, we propose to investigate the entity-based MIE tasks under the low-resource settings. The conventional models are prone to overfitting on limited labeled data, which can result in poor performance. This is because the models tend to learn the bias existing in the limited samples, which can lead them to model the spurious correlations between multimodal features and task labels. To provide a more comprehensive understanding of the bias inherent in multimodal features of MIE samples, we decompose the features into image, entity, and context factors. Furthermore, we investigate the causal relationships between these factors and model performance, leveraging the structural causal model to delve into the correlations between the input features and output labels. Based on this, we propose the multimodal counterfactual instance learning framework to generate the counterfactual instances by the interventions on the limited observational samples. In the framework, we analyze the causal effect of the counterfactual instances and exploit it as a supervisory signal to maximize the effect for reducing the bias and improving the generalization of the model. Empirically, we evaluate the proposed method on the two public MIE benchmark datasets and the experimental results verify the effectiveness of it.

Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue. However, most previous work trained independent retrievers for each specific resource, resulting in sub-optimal performance and low efficiency. Thus, we propose a multi-task framework function as a universal retriever for three dominant retrieval tasks during the conversation: persona selection, knowledge selection, and response selection. To this end, we design a dual-encoder architecture consisting of a context-adaptive dialogue encoder and a candidate encoder, aiming to attention to the relevant context from the long dialogue and retrieve suitable candidates by simply a dot product. Furthermore, we introduce two loss constraints to capture the subtle relationship between dialogue context and different candidates by regarding historically selected candidates as hard negatives. Extensive experiments and analysis establish state-of-the-art retrieval quality both within and outside its training domain, revealing the promising potential and generalization capability of our model to serve as a universal retriever for different candidate selection tasks simultaneously.

Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costly to transfer. To tackle this challenge, this paper proposed a retrieval-free approach, KiDG, by automatically turning knowledge documents into simulated multi-turn dialogues through a Multi-Document Traversal algorithm. The simulated knowledge-intensive dialogues constructed by KiDG in one domain can be easily used to train and enhance pre-trained dialogue models’ knowledge w.r.t. this domain without costly annotation. We conduct extensive experiments comparing retrieval-augmented models and a variety of retrieval-free models. We found that dialogue models enhanced with data simulated with KiDG largely outperform state-of-the-art retrieval-free methods, and it achieves comparable performance compared to retrieval-augmented methods while being better, and cheaper at domain transfer.

Generating persona consistent dialogue response is important for developing an intelligent conversational agent. Recent works typically fine-tune large-scale pre-trained models on this task by concatenating persona texts and dialogue history as a single input sequence to generate the target response. While simple and effective, our analysis shows that this popular practice is seriously affected by order sensitivity where different input orders of persona sentences significantly impact the quality and consistency of generated response, resulting in severe performance fluctuations (i.e., 29.4% on GPT2 and 83.2% on BART). To mitigate the order sensitivity problem, we propose a model-agnostic framework, ORder Insensitive Generation (ORIG), which enables dialogue models to learn robust representation under different persona orders and improve the consistency of response generation. Experiments on the Persona-Chat dataset justify the effectiveness and superiority of our method with two dominant pre-trained models (GPT2 and BART).

Knowledge probing is a task to assess the knowledge encoded within pre-trained language models (PLMs) by having the PLM complete prompts such as “Italy is located in __,”. The model’s prediction precision serves as a lower bound for the amount of knowledge it contains. Subsequent works explore training a series of vectors as prompts to guide PLMs towards more accurate predictions. However, these methods compromise the readability of the prompts. We cannot directly understand these prompts from their literal meaning, making it difficult to verify whether they are correct. Consequently, the credibility of probing results derived from these prompts is diminished. To address the issue, we propose a novel method called ReadPrompt, which aims to identify meaningful sentences to serve as prompts. Experiments show that ReadPrompt achieves state-of-the-art performance on the current knowledge probing benchmark. Moreover, since the prompt is readable, we discovered a misalignment between constructed prompts and knowledge, which is also present in current prompting methods verified by an attack experiment. We claim that the probing outcomes of the current prompting methods are unreliable that overestimate the knowledge contained within PLMs.

Pretrained language models (PLMs) based knowledge-grounded dialogue systems are prone to generate responses that are factually inconsistent with the provided knowledge source. In such inconsistent responses, the dialogue models fail to accurately express the external factual knowledge they rely upon. Inspired by previous work which identified that feedforward networks (FFNs) within Transformers are responsible for factual knowledge expressions, we investigate two methods to efficiently improve the factual expression capability of FFNs by knowledge enhancement and alignment respectively. We first propose K-Dial, which explicitly introduces extended FFNs in Transformers to enhance factual knowledge expressions given the specific patterns of knowledge-grounded dialogue inputs. Additionally, we apply the reinforcement learning for factual consistency (RLFC) method to implicitly adjust FFNs’ expressions in responses by aligning with gold knowledge for the factual consistency preference. To comprehensively assess the factual consistency and dialogue quality of responses, we employ extensive automatic measures and human evaluations including sophisticated fine-grained NLI-based metrics. Experimental results on WoW and CMU_DoG datasets demonstrate that our methods efficiently enhance the ability of the FFN module to convey factual knowledge, validating the efficacy of improving factual consistency for knowledge-grounded dialogue systems.

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses.

Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, they still possess limitations, such as failing to ask clarifying questions to ambiguous queries or refuse users’ unreasonable requests, both of which are considered as key aspects of a conversational agent’s proactivity. This raises the question of whether LLM-based conversational systems are equipped to handle proactive dialogue problems. In this work, we conduct a comprehensive analysis of LLM-based conversational systems, specifically focusing on three key aspects of proactive dialogues: clarification, target-guided, and non-collaborative dialogues. To trigger the proactivity of LLMs, we propose the Proactive Chain-of-Thought prompting scheme, which augments LLMs with the goal planning capability over descriptive reasoning chains. Empirical findings are discussed to promote future studies on LLM-based proactive dialogue systems.

Large Language Models (LLMs), such as ChatGPT, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cues about the user status exhibited in the context. Such in-depth dialogue scenarios are challenging for existing LLMs to figure out the user’s hidden needs and respond satisfactorily through a single-step inference. To this end, we propose a novel linguistic cue-based chain-of-thoughts (Cue-CoT), which enhances the LLMs inference with an intermediate reasoning step to find cues exhibited in the dialogue, aiming to provide a more personalized and engaging response. To evaluate the approach, we build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English, targeting 3 major linguistic cues during the conversation: personality, emotion, and psychology. We conducted experiments on the proposed benchmark with 5 LLMs under both zero-shot and one-shot settings. Empirical results demonstrate our proposed Cue-CoT method outperforms standard prompting methods in terms of both helpfulness and acceptability on all datasets.

News recommendation (NR) is essential for online news services. Existing NR methods typically adopt a news-user representation learning framework, facing two potential limitations. First, in news encoder, single candidate news encoding suffers from an insufficient semantic information problem. Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal. To overcome these limitations, we propose dual-interactive graph attention networks (DIGAT) consisting of news- and user-graph channels. In the news-graph channel, we enrich the semantics of single candidate news by incorporating the semantically relevant news information with a semantic-augmented graph (SAG). In the user-graph channel, multi-level user interests are represented with a news-topic graph. Most notably, we design a dual-graph interaction process to perform effective feature interaction between the news and user graphs, which facilitates accurate news-user representation matching. Experiment results on the benchmark dataset MIND show that DIGAT outperforms existing news recommendation methods. Further ablation studies and analyses validate the effectiveness of (1) semantic-augmented news graph modeling and (2) dual-graph interaction.

This paper describes our system submitted to task 4 of SemEval 2020: Commonsense Validation and Explanation (ComVE) which consists of three sub-tasks. The task is to directly validate the given sentence whether or not to make sense and require the model to explain it. Based on BERT architecture with the multi-task setting, we propose an effective and interpretable “Explain, Reason and Predict” (ERP) system to solve the three sub-tasks about commonsense: (a) Validation, (b) Reasoning, and (c) Explanation. Inspired by cognitive studies of common sense, our system first generates a reason or understanding of the sentences and then choose which one statement makes sense, which is achieved by multi-task learning. During the post-evaluation, our system has reached 92.9% accuracy in subtask A (rank 11), 89.7% accuracy in subtask B (rank 9), and BLEU score of 12.9 in subtask C (rank 8).