Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations. A significant type of this issue is the false premise hallucination, which we define as the phenomenon when LLMs generate hallucinated text when confronted with false premise questions. In this paper, we perform a comprehensive analysis of the false premise hallucination and elucidate its internal working mechanism: a small subset of attention heads (which we designate as false premise heads) disturb the knowledge extraction process, leading to the occurrence of false premise hallucination. Based on our analysis, we propose FAITH (False premise Attention head constraIining for miTigating Hallucinations), a novel and effective method to mitigate false premise hallucinations. It constrains the false premise attention heads during the model inference process. Impressively, extensive experiments demonstrate that constraining only approximately 1% of the attention heads in the model yields a notable increase of nearly 20% of model performance.

Planning, as the core module of agents, is crucial in various fields such as embodied agents, web navigation, and tool using. With the development of large language models (LLMs), some researchers treat large language models as intelligent agents to stimulate and evaluate their planning capabilities. However, the planning mechanism is still unclear. In this work, we focus on exploring the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations. First, we study how planning is done internally by analyzing the multi-layer perception (MLP) and multi-head self-attention (MHSA) components at the last token. We find that the output of MHSA in the middle layers at the last token can directly decode the decision to some extent. Based on this discovery, we further trace the source of MHSA by information flow, and we reveal that MHSA extracts information from spans of the goal states and recent steps. According to information flow, we continue to study what information is encoded within it. Specifically, we explore whether future decisions have been considered in advance in the representation of flow. We demonstrate that the middle and upper layers encode a few short-term future decisions. Overall, our research analyzes the look-ahead planning mechanisms of LLMs, facilitating future research on LLMs performing planning tasks.

Recently, retrieval augmentation and tool augmentation have demonstrated a remarkable capability to expand the internal memory boundaries of language models (LMs) by providing external context. However, internal memory and external context inevitably clash, leading to knowledge conflicts within LMs. In this paper, we aim to interpret the mechanism of knowledge conflicts through the lens of information flow, and then mitigate conflicts by precise interventions at the pivotal point. We find there are some attention heads with opposite effects in the later layers, where memory heads can recall knowledge from internal memory, and context heads can retrieve knowledge from external context. Moreover, we reveal that the pivotal point at which knowledge conflicts emerge in LMs is the integration of inconsistent information flows by memory heads and context heads. Inspired by the insights, we propose a novel method called Pruning Head via PatH PatcHing (PH3), which can efficiently mitigate knowledge conflicts by pruning conflicting attention heads without updating model parameters. PH3 can flexibly control eight LMs to use internal memory (↑ 44.0%) or external context (↑ 38.5%). Moreover, PH3 can also improve the performance of LMs on open-domain QA tasks. We also conduct extensive experiments to demonstrate the cross-model, cross-relation, and cross-format generalization of our method. Our code is publicly available at https://github.com/jinzhuoran/MConflict/.

Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or employing self-enhancement methods to elicit knowledge in LLMs. However, noisy knowledge and invalid reasoning issues hamper their ability to answer questions accurately. To this end, we propose a novel method named eliciting, filtering and integrating knowledge in large language model (LINKED). In it, we design a reward model to filter out the noisy knowledge and take the marginal consistent reasoning module to reduce invalid reasoning. With our comprehensive experiments on two complex commonsense reasoning benchmarks, our method outperforms SOTA baselines (up to 9.0% improvement of accuracy). Besides, to measure the positive and negative impact of the injected knowledge, we propose a new metric called effectiveness-preservation score for the knowledge enhancement works. Finally, through extensive experiments, we conduct an in-depth analysis and find many meaningful conclusions about LLMs in commonsense reasoning tasks.

With the development of deep learning, natural language processing technology has effectively improved the efficiency of various aspects of the traditional judicial industry. However, most current efforts focus on tasks within individual judicial stages, making it difficult to handle complex tasks that span multiple stages. As the autonomous agents powered by large language models are becoming increasingly smart and able to make complex decisions in real-world settings, offering new insights for judicial intelligence. In this paper, (1) we propose a novel multi-agent framework, AgentsCourt, for judicial decision-making. Our framework follows the classic court trial process, consisting of court debate simulation, legal resources retrieval and decision-making refinement to simulate the decision-making of judge. (2) we introduce SimuCourt, a judicial benchmark that encompasses 420 Chinese judgment documents, spanning the three most common types of judicial cases. Furthermore, to support this task, we construct a large-scale legal knowledge base, Legal-KB, with multi-resource legal knowledge. (3) Extensive experiments show that our framework outperforms the existing advanced methods in various aspects, especially in generating legal articles, where our model achieves significant improvements of 8.6% and 9.1% F1 score in the first and second instance settings, respectively.

Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). However, we find these CoT-like methods lead to a considerable number of originally correct answers turning wrong, which we define as the Toxic CoT problem. To interpret and mitigate this problem, we first utilize attribution tracing and causal tracing methods to probe the internal working mechanism of the LLM during CoT reasoning. Through comparisons, we prove that the model exhibits information loss from the question over the shallow attention layers when generating rationales or answers. Based on the probing findings, we design a novel method called RIDERS (Residual decodIng and sERial-position Swap), which compensates for the information deficit in the model from both decoding and serial-position perspectives. Through extensive experiments on multiple commonsense reasoning benchmarks, we validate that this method not only significantly eliminates Toxic CoT problems (decreased by 23.6%), but also effectively improves the model’s overall commonsense reasoning performance (increased by 5.5%).

Adjusting the outdated behaviors of large langugae models (LLMs) after deployment remains a significant challenge. It motivates the model editing research, which is however mainly explored in a restricted task form with triple-based edit requests. Recent works have initiated a transition to a more practical and unified editing task that takes free-form text as edit requests. However, there are gaps in nuanced benchmark designs and re-evaluation of existing methods. To bridge the gaps, we introduce a multi-level benchmark for free text model editing (MULFE). The benchmark categorizes probe queries into three levels of generalization, ranging from basic literal memory to deeper understanding and reasoning. Based on the benchmark, we conduct extensive experiments across various base models, edit sizes, and editing methods, including adaptations of mainstream locate-and-edit and hypernetwork methods. The results highlight the inconsistent behaviors of edited models on different generalization levels. Higher-level generalization remains a significant challenge. Based on the findings, we propose SIDE, a simple yet effective method based on in-context distillation to enhance the generalization performance. The benchmark dataset and evaluation scripts are publicly available at http://github.com/wchrepo/mulfe.

Retrieval-augmented language models (RALMs) have demonstrated significant potential in refining and expanding their internal memory by retrieving evidence from external sources. However, RALMs will inevitably encounter knowledge conflicts when integrating their internal memory with external sources. Knowledge conflicts can ensnare RALMs in a tug-of-war between knowledge, limiting their practical applicability. In this paper, we focus on exploring and resolving knowledge conflicts in RALMs. First, we present an evaluation framework for assessing knowledge conflicts across various dimensions. Then, we investigate the behavior and preference of RALMs from the following two perspectives: (1) Conflicts between internal memory and external sources: We find that stronger RALMs emerge with the Dunning-Kruger effect, persistently favoring their faulty internal memory even when correct evidence is provided. Besides, RALMs exhibit an availability bias towards common knowledge; (2) Conflicts between truthful, irrelevant and misleading evidence: We reveal that RALMs follow the principle of majority rule, leaning towards placing trust in evidence that appears more frequently. Moreover, we find that RALMs exhibit confirmation bias, and are more willing to choose evidence that is consistent with their internal memory. To solve the challenge of knowledge conflicts, we propose a method called Conflict-Disentangle Contrastive Decoding (CD2) to better calibrate the model’s confidence. Experimental results demonstrate that our CD2 can effectively resolve knowledge conflicts in RALMs.

Event Causality Identification (ECI) refers to the detection of causal relations between events in texts. However, most existing studies focus on sentence-level ECI with high-resource languages, leaving more challenging document-level ECI (DECI) with low-resource languages under-explored. In this paper, we propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning (GIMC) for zero-shot cross-lingual document-level ECI. Specifically, we introduce a heterogeneous graph interaction network to model the long-distance dependencies between events that are scattered over a document. Then, to improve cross-lingual transferability of causal knowledge learned from the source language, we propose a multi-granularity contrastive transfer learning module to align the causal representations across languages. Extensive experiments show our framework outperforms the previous state-of-the-art model by 9.4% and 8.2% of average F1 score on monolingual and multilingual scenarios respectively. Notably, in the multilingual scenario, our zero-shot framework even exceeds GPT-3.5 with few-shot learning by 24.3% in overall performance.

Compared to traditional single-turn ad-hoc retrieval, conversational retrieval needs to handle the multi-turn conversation and understand the user’s real query intent. However, most existing methods simply fine-tune the pre-trained ad-hoc retriever on limited supervised data, making it challenging for the retriever to fully grasp the entirety of the conversation. In this paper, we find that large language models (LLMs) can accurately discover the user’s query intent from the complex conversation context and provide the supervised signal to instruct the retriever in an unsupervised manner. Therefore, we propose a novel method termed InstructoR to Instruct unsupervised conversational dense Retrieval with LLMs. We design an unsupervised training framework that employs LLMs to estimate the session-passage relevance score as the soft label to guide the retriever’s training. Specially, we devise three instructing strategies from context, query and response perspectives to calculate the relevance score more precisely, including conversational retrieval as conversation generation, question rewrite as latent variable and question response as posterior guide. Experimental results show InstructoR can bring significant improvements across various ad-hoc retrievers, even surpassing the current supervised state-of-the-art method. We also demonstrate the effectiveness of our method under low-resource and zero-shot settings. Our code is publicly available at https://github.com/jinzhuoran/InstructoR/.

Despite the significant progress in developing named entity recognition models, scaling to novel-emerging types still remains challenging in real-world scenarios. Continual learning and zero-shot learning approaches have been explored to handle novel-emerging types with less human supervision, but they have not been as successfully adopted as supervised approaches. Meanwhile, humans possess a much larger vocabulary size than these approaches and have the ability to learn the alignment between entities and concepts effortlessly through natural supervision. In this paper, we consider a more realistic and challenging setting called open-vocabulary named entity recognition (OVNER) to imitate human-level ability. OVNER aims to recognize entities in novel types by their textual names or descriptions. Specifically, we formulate OVNER as a semantic matching task and propose a novel and scalable two-stage method called Context-Type SemAntiC Alignment and FusiOn (CACAO). In the pre-training stage, we adopt Dual-Encoder for context-type semantic alignment and pre-train Dual-Encoder on 80M context-type pairs which are easily accessible through natural supervision. In the fine-tuning stage, we use Cross-Encoder for context-type semantic fusion and fine-tune Cross-Encoder on base types with human supervision. Experimental results show that our method outperforms the previous state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types. Moreover, CACAO also demonstrates its flexible transfer ability in cross-domain NER.

In this paper, we propose CogKGE, a knowledge graph embedding (KGE) toolkit, which aims to represent multi-source and heterogeneous knowledge. For multi-source knowledge, unlike existing methods that mainly focus on entity-centric knowledge, CogKGE also supports the representations of event-centric, commonsense and linguistic knowledge. For heterogeneous knowledge, besides structured triple facts, CogKGE leverages additional unstructured information, such as text descriptions, node types and temporal information, to enhance the meaning of embeddings. Designing CogKGE aims to provide a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks. As a research framework, CogKGE consists of five parts, including core, data, model, knowledge and adapter module. As a knowledge discovery toolkit, CogKGE provides pre-trained embedders to discover new facts, cluster entities and check facts. Furthermore, we construct two benchmark datasets for further research on multi-source heterogeneous KGE tasks: EventKG240K and CogNet360K. We also release an online system to discover knowledge visually. Source code, datasets and pre-trained embeddings are publicly available at GitHub, with a short instruction video.

The task of knowledge graph entity typing (KGET) aims to infer the missing types for entities in knowledge graphs. Some pioneering work has proved that neighbor information is very important for the task. However, existing methods only leverage the one-hop neighbor information of the central entity, ignoring the multi-hop neighbor information that can provide valuable clues for inference. Besides, we also observe that there are co-occurrence relations between types, which is very helpful to alleviate false-negative problem. In this paper, we propose a novel method called Mining Treasured Neighbors (MiNer) to make use of these two characteristics. Firstly, we devise a Neighbor Information Aggregation module to aggregate the neighbor information. Then, we propose an Entity Type Inference module to mitigate the adverse impact of the irrelevant neighbor information. Finally, a Type Co-occurrence Regularization module is designed to prevent the model from overfitting the false negative examples caused by missing types. Experimental results on two widely used datasets indicate that our approach significantly outperforms previous state-of-the-art methods.

As the first step of modern natural language processing, text representation encodes discrete texts as continuous embeddings. Pre-trained language models (PLMs) have demonstrated strong ability in text representation and significantly promoted the development of natural language understanding (NLU). However, existing PLMs represent a text solely by its context, which is not enough to support knowledge-intensive NLU tasks. Knowledge is power, and fusing external knowledge explicitly into PLMs can provide knowledgeable text representations. Since previous knowledge-enhanced methods differ in many aspects, making it difficult for us to reproduce previous methods, implement new methods, and transfer between different methods. It is highly desirable to have a unified paradigm to encompass all kinds of methods in one framework. In this paper, we propose CogKTR, a knowledge-enhanced text representation toolkit for natural language understanding. According to our proposed Unified Knowledge-Enhanced Paradigm (UniKEP), CogKTR consists of four key stages, including knowledge acquisition, knowledge representation, knowledge injection, and knowledge application. CogKTR currently supports easy-to-use knowledge acquisition interfaces, multi-source knowledge embeddings, diverse knowledge-enhanced models, and various knowledge-intensive NLU tasks. Our unified, knowledgeable and modular toolkit is publicly available at GitHub, with an online system and a short instruction video.

CogNet is a knowledge base that integrates three types of knowledge: linguistic knowledge, world knowledge and commonsense knowledge. In this paper, we propose an information extraction toolkit, called CogIE, which is a bridge connecting raw texts and CogNet. CogIE has three features: versatile, knowledge-grounded and extensible. First, CogIE is a versatile toolkit with a rich set of functional modules, including named entity recognition, entity typing, entity linking, relation extraction, event extraction and frame-semantic parsing. Second, as a knowledge-grounded toolkit, CogIE can ground the extracted facts to CogNet and leverage different types of knowledge to enrich extracted results. Third, for extensibility, owing to the design of three-tier architecture, CogIE is not only a plug-and-play toolkit for developers but also an extensible programming framework for researchers. We release an open-access online system to visually extract information from texts. Source code, datasets and pre-trained models are publicly available at GitHub, with a short instruction video.