51 accepted papers
Despite the advancing reasoning capabilities of large language models (LLMs), many reasoning evaluations are increasingly compromised by data contamination, which induces unreliable **contaminated reasoning** on leaked inputs. While this phenomenon is widely observed, its underlying mechanism remain…
Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outp
Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time reward model (RM)-based reasoning as a critical yet overlooked a…
Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathematical reasoning. Despite their promise, MLLMs’ reasoning abilities across different scenarios in real life remain largely…
The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on understanding tasks, which only require models to match frames mentioned…
Reward models (RMs) play a critical role in aligning AI behaviors with human preferences, yet they face two fundamental challenges: (1) Modality Imbalance, where most RMs are mainly focused on text and image modalities, offering limited support for video, audio, and other modalities; and (2) Prefere…
The fundamental representational units (FRUs) of large language models (LLMs) remain undefined, limiting further understanding of their underlying mechanisms. In this paper, we introduce ***Atom Theory*** to systematically define, evaluate, and identify such FRUs, which we term atoms. Building on th…
With the development of large language models, they are widely used as agents in various fields. A key component of agents is memory, which stores vital information but is susceptible to jailbreak attacks. Existing research mainly focuses on single-agent attacks and shared memory attacks. However, r…
As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations in a lack of external feedback, these agents struggle with self-correction and generalization. A promising approach is to…
Large language models (LLMs) have achieved remarkable success but still tend to generate factually erroneous responses, a phenomenon known as hallucination. A recent trend is to use preference learning to fine-tune models to align with factuality. However, existing work primarily evaluates fine-tune…
Tool learning enables Large Language Models (LLMs) to interact with the external environment by invoking tools, enriching the accuracy and capability scope of LLMs. However, previous works predominantly focus on improving the model's tool-utilizing accuracy and the ability to generalize to new, unse…
Knowledge neuron theory provides a key approach to understanding the mechanisms of factual knowledge in Large Language Models (LLMs), which suggests that facts are stored within multi-layer perceptron neurons. This paper further explores **Degenerate Knowledge Neurons** (DKNs), where distinct sets o…
Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. However, most of the current benchmarks primarily focus on either personalization of text generation or direct tool-utilizing, without considering bo…
Large language models (LLMs) store extensive factual knowledge, but the mechanisms behind how they store and express this knowledge remain unclear. The Knowledge Neuron (KN) thesis is a prominent theory for explaining these mechanisms. This theory is based on the **Knowledge Localization (KL)** assu…
Knowledge editing aims to update outdated or incorrect knowledge in large language models (LLMs). However, current knowledge editing methods have limited scalability for lifelong editing. This study explores the fundamental reason why knowledge editing fails in lifelong editing. We begin with the cl…
Multimodal knowledge editing is an important method for modifying outdated or incorrect knowledge in Multimodal Large Language Models (MLLMs). However, existing datasets for multimodal knowledge editing lack multi-granularity knowledge. In this paper, we present a more realistic dataset called M2Edi
Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and then apply them to unseen examples. We present {\scshape Mirage}, a synthetic dataset that addresses the limitations of…
Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the alignment process, reward models (RMs) act as a crucial proxy for…
Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-perfect performance on conventional metrics, the models edited by them are still prone to generating original knowledge. T…
We demonstrate that features, rather than neurons, serve as superior analytical units for understanding the mechanisms of factual knowledge in Language Models (LMs). Previous studies primarily utilize MLP neurons as units of analysis; however, neurons suffer from polysemanticity, leading to limited…
Chain-of-thought (CoT) prompting demonstrates varying performance under different reasoning tasks.Previous work attempts to evaluate it but falls short in providing an in-depth analysis of patterns that influence the CoT. In this paper, we study the CoT performance from the perspective of effectiven…
LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain vulnerable to adversarial queries and the unlearned knowledge resu…
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 t…
Traditional continual event detection relies on abundant labeled data for training, which is often impractical to obtain in real-world applications. In this paper, we introduce continual few-shot event detection (CFED), a more commonly encountered scenario when a substantial number of labeled sample…
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.…
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 i…
Pre-trained language models (PLMs) contain vast amounts of factual knowledge, but how the knowledge is stored in the parameters remains unclear. This paper delves into the complex task of understanding how factual knowledge is stored in multilingual PLMs, and introduces the Architecture-adapted Mult…
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.…
Recent work shows large language models can be prompted to generate useful rationales for commonsense question answering (CQA), which can improve the performance of both themselves and other models. However, the cost of deployment and further tuning is relatively expensive for the large models. Some…
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 p…
Data is one of the most critical elements in building a large language model. However, existing systems either fail to customize a corpus curation pipeline or neglect to leverage comprehensive corpus assessment for iterative optimization of the curation. To this end, we present a pretraining corpus…
Large language models (LLMs) inevitably memorize sensitive, copyrighted, and harmful knowledge from the training corpus; therefore, it is crucial to erase this knowledge from the models. Machine unlearning is a promising solution for efficiently removing specific knowledge by post hoc modifying mode…
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.…
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…
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.…
Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge. However, current knowledge editing methods primarily focus on single editing, failing to meet the requirements for lifelong editing. This study reveals a perf…
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 pa…
The swift advancement in large language models (LLMs) has heightened the importance of model evaluations. LLMs have acquired a substantial amount of knowledge, and evaluating the knowledge of these LLMs is crucial. To address this, we introduce the ZhuJiu-Knowledge benchmark which carefully consider…
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 t…
The concept of a complex event schema pertains to the graph structure that represents real-world knowledge of events and their multi-dimensional relationships. However, previous studies on event schema induction have been hindered by challenges such as error propagation and data quality issues. To t…
Sequence Labeling (SL) is long-standing in Natural Language Processing (NLP). Traditionally, discriminative models have been widely used to capture the conditional distribution of sequence tags, rather than generative models. In this paper, we present DiffusionSL, a framework that utilizes a conditi…
Traditional event detection methods require predefined event schemas. However, manually defining event schemas is expensive and the coverage of schemas is limited. To this end, some works study the event type induction (ETI) task, which discovers new event types via clustering. However, the setting…
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 f…
Causality Explanation Generation refers to generate an explanation in natural language given an initial cause-effect pair. It demands rigorous explicit rationales to demonstrate the acquisition of implicit commonsense knowledge, which is unlikely to be easily memorized, making it challenging for lar…
Event argument extraction (EAE) aims to identify the arguments of a given event, and classify the roles that those arguments play. Due to high data demands of training EAE models, zero-shot cross-lingual EAE has attracted increasing attention, as it greatly reduces human annotation effort. Some prio…
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,…
The ICD coding task aims at assigning codes of the International Classification of Diseases in clinical notes. Since manual coding is very laborious and prone to errors, many methods have been proposed for the automatic ICD coding task. However, existing works either ignore the long-tail of code fre…
Dialogue state tracking (DST), which estimates user goals given a dialogue context, is an essential component of task-oriented dialogue systems. Conventional DST models are usually trained offline, which requires a fixed dataset prepared in advance. This paradigm is often impractical in real-world a…
Identifying causal relations of events is an important task in natural language processing area. However, the task is very challenging, because event causality is usually expressed in diverse forms that often lack explicit causal clues. Existing methods cannot handle well the problem, especially in…
Modern models for event causality identification (ECI) are mainly based on supervised learning, which are prone to the data lacking problem. Unfortunately, the existing NLP-related augmentation methods cannot directly produce available data required for this task. To solve the data lacking problem,…
Event factuality indicates the degree of certainty about whether an event occurs in the real world. Existing studies mainly focus on identifying event factuality at sentence level, which easily leads to conflicts between different mentions of the same event. To this end, we study the problem of docu…