Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning, which integrates LLMs with external tools to address diverse real-world challenges. Assessing the capability of LLMs to utilise tools necessitates large-scale and stable benchmarks. However, previous works relied on either hand-crafted online tools with limited scale, or large-scale real online APIs suffering from instability of API status. To address this problem, we introduce StableToolBench, a benchmark evolving from ToolBench, proposing a virtual API server and stable evaluation system. The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status. Meanwhile, the stable evaluation system designs solvable pass and win rates using GPT-4 as the automatic evaluator to eliminate the randomness during evaluation. Experimental results demonstrate the stability of StableToolBench, and further discuss the effectiveness of API simulators, the caching system, and the evaluator system.

Recent work has made a preliminary attempt to use large language models (LLMs) to solve the stance detection task, showing promising results. However, considering that stance detection usually requires detailed background knowledge, the vanilla reasoning method may neglect the domain knowledge to make a professional and accurate analysis. Thus, there is still room for improvement of LLMs reasoning, especially in leveraging the generation capability of LLMs to simulate specific experts (i.e., multi-agents) to detect the stance. In this paper, different from existing multi-agent works that require detailed descriptions and use fixed experts, we propose a Dynamic Experienced Expert Modeling (DEEM) method which can leverage the generated experienced experts and let LLMs reason in a semi-parametric way, making the experts more generalizable and reliable. Experimental results demonstrate that DEEM consistently achieves the best results on three standard benchmarks, outperforms methods with self-consistency reasoning, and reduces the bias of LLMs.

Large language models (LLMs) have been widely studied for their ability to store and utilize positive knowledge. However, negative knowledge, such as “lions don’t live in the ocean”, is also ubiquitous in the world but rarely mentioned explicitly in text. What do LLMs know about negative knowledge?This work examines the ability of LLMs on negative commonsense knowledge. We design a constrained keywords-to-sentence generation task (CG) and a Boolean question answering task (QA) to probe LLMs.Our experiments reveal that LLMs frequently fail to generate valid sentences grounded in negative commonsense knowledge, yet they can correctly answer polar yes-or-no questions. We term this phenomenon the belief conflict of LLMs.Our further analysis shows that statistical shortcuts and negation reporting bias from language modeling pre-training cause this conflict.

Pre-trained language models (PLMs) have been widely used to underpin various downstream tasks. However, the adversarial attack task has found that PLMs are vulnerable to small perturbations. Mainstream methods adopt a detached two-stage framework to attack without considering the subsequent influence of substitution at each step. In this paper, we formally model the adversarial attack task on PLMs as a sequential decision-making problem, where the whole attack process is sequential with two decision-making problems, i.e., word finder and word substitution. Considering the attack process can only receive the final state without any direct intermediate signals, we propose to use reinforcement learning to find an appropriate sequential attack path to generate adversaries, named SDM-ATTACK. Our experimental results show that SDM-ATTACK achieves the highest attack success rate with a comparable modification rate and semantic similarity to attack fine-tuned BERT. Furthermore, our analyses demonstrate the generalization and transferability of SDM-ATTACK.Resources of this work will be released after this paper’s publication.

Retrieval-augmented methods have received increasing attention to support downstream tasks by leveraging useful information from external resources. Recent studies mainly focus on exploring retrieval to solve knowledge-intensive (KI) tasks. However, the potential of retrieval for most non-knowledge-intensive (NKI) tasks remains under-explored. There are two main challenges to leveraging retrieval-augmented methods for NKI tasks: 1) the demand for diverse relevance score functions and 2) the dilemma between training cost and task performance. To address these challenges, we propose a two-stage framework for NKI tasks, named PGRA. In the first stage, we adopt a task-agnostic retriever to build a shared static index and select candidate evidence efficiently. In the second stage, we design a prompt-guided reranker to rerank the nearest evidence according to task-specific relevance for the reader. Experimental results show that PGRA outperforms other state-of-the-art retrieval-augmented methods. Our analyses further investigate the influence factors to model performance and demonstrate the generality of PGRA. The code and model will be released for further research.

Simile interpretation is a crucial task in natural language processing. Nowadays, pre-trained language models (PLMs) have achieved state-of-the-art performance on many tasks. However, it remains under-explored whether PLMs can interpret similes or not. In this paper, we investigate the ability of PLMs in simile interpretation by designing a novel task named Simile Property Probing, i.e., to let the PLMs infer the shared properties of similes. We construct our simile property probing datasets from both general textual corpora and human-designed questions, containing 1,633 examples covering seven main categories. Our empirical study based on the constructed datasets shows that PLMs can infer similes’ shared properties while still underperforming humans. To bridge the gap with human performance, we additionally design a knowledge-enhanced training objective by incorporating the simile knowledge into PLMs via knowledge embedding methods. Our method results in a gain of 8.58% in the probing task and 1.37% in the downstream task of sentiment classification. The datasets and code are publicly available at https://github.com/Abbey4799/PLMs-Interpret-Simile.

Pretrained language models such as BERT have been successfully applied to a wide range of natural language processing tasks and also achieved impressive performance in document reranking tasks. Recent works indicate that further pretraining the language models on the task-specific datasets before fine-tuning helps improve reranking performance. However, the pre-training tasks like masked language model and next sentence prediction were based on the context of documents instead of encouraging the model to understand the content of queries in document reranking task. In this paper, we propose a new self-supervised joint training framework (SJTF) with a self-supervised method called Masked Query Prediction (MQP) to establish semantic relations between given queries and positive documents. The framework randomly masks a token of query and encodes the masked query paired with positive documents, and uses a linear layer as a decoder to predict the masked token. In addition, the MQP is used to jointly optimize the models with supervised ranking objective during fine-tuning stage without an extra further pre-training stage. Extensive experiments on the MS MARCO passage ranking and TREC Robust datasets show that models trained with our framework obtain significant improvements compared to original models.