Despite near-perfect results in artificial evaluations, the effectiveness of model editing in real-world applications remains unexplored. To bridge this gap, we propose to study model editing in question answering (QA) by establishing a rigorous evaluation practice to assess the effectiveness of editing methods in correcting LLMs' errors. It consists of QAEdit, a new benchmark derived from popular QA datasets, and a standardized evaluation framework. Our single editing experiments indicate that current editing methods perform substantially worse than previously reported (38.5% vs. ~96%). Through module analysis and controlled experiments, we demonstrate that this performance decline stems from issues in evaluation practices of prior editing research. One key issue is the inappropriate use of teacher forcing in testing prevents error propagation by feeding ground truth tokens (inaccessible in real-world scenarios) as input. Furthermore, we simulate real-world deployment by sequential editing, revealing that current approaches fail drastically with only 1000 edits. Our analysis provides a fundamental reexamination of both the real-world applicability of existing model editing methods and their evaluation practices, and establishes a rigorous evaluation framework with key insights to advance reliable and practical model editing research.

Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on hand-crafted prompts, difficulty in multi-step planning, and lack of precise error diagnosis and reflection mechanisms. We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task. Inspired by software engineering principles, ToolCoder transforms natural language queries into structured Python function scaffold and systematically breaks down tasks with descriptive comments, enabling LLMs to leverage coding paradigms for complex reasoning and planning. It then generates and executes function implementations to obtain final responses. Additionally, ToolCoder stores successfully executed functions in a repository to promote code reuse, while leveraging error traceback mechanisms for systematic debugging, optimizing both execution efficiency and robustness. Experiments demonstrate that ToolCoder achieves superior performance in task completion accuracy and execution reliability compared to existing approaches, establishing the effectiveness of code-centric approaches in tool learning.

Retrieval-augmented generation (RAG) systems often suffer from performance degradation when encountering noisy or irrelevant documents, driving researchers to develop sophisticated training strategies to enhance their robustness against such retrieval noise. However, as large language models (LLMs) continue to advance, the necessity of these complex training methods is increasingly questioned. In this paper, we systematically investigate whether complex robust training strategies remain necessary as model capacity grows. Through comprehensive experiments spanning multiple model architectures and parameter scales, we evaluate various document selection methods and adversarial training techniques across diverse datasets. Our extensive experiments consistently demonstrate that as models become more powerful, the performance gains brought by complex robust training methods drop off dramatically. We delve into the rationale and find that more powerful models inherently exhibit superior confidence calibration, better generalization across datasets (even when trained with randomly selected documents), and optimal attention mechanisms learned with simpler strategies. Our findings suggest that RAG systems can benefit from simpler architectures and training strategies as models become more powerful, enabling more scalable applications with minimal complexity.

A new trend uses LLMs as dense text encoders via contrastive learning. However, since LLM embeddings predict the probability distribution of the next token, they are inherently generative and distributive, conflicting with contrastive learning, which requires embeddings to capture full-text semantics and align via cosine similarity. This discrepancy hinders the full utilization of LLMs' pre-training capabilities, resulting in inefficient learning. In response to this issue, we propose AutoRegEmbed, a new contrastive learning method built on embedding conditional probability distributions, which integrates two core tasks: information compression and conditional distribution alignment. The information compression task encodes text into the embedding space, ensuring that the embedding vectors capture global semantics. The conditional distribution alignment task focuses on aligning text embeddings with positive samples embeddings by leveraging the conditional distribution of embeddings while simultaneously reducing the likelihood of generating negative samples from text embeddings, thereby achieving embedding alignment and uniformity. Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches and achieves performance comparable to state-of-the-art models when using the same amount of data.

Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a single entity to ensure comprehensive and consistent updates to entity-centric knowledge. Through preliminary observation, we identify a significant challenge: Current state-of-the-art editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject. To address the lack of relevant editing data for identical subjects in traditional benchmarks, we introduce the $\text{S}^2\text{RKE}$(Same-Subject Related Knowledge Editing) benchmark. Our extensive experiments reveal that only mainstream locate-then-edit methods, such as ROME and MEMIT, exhibit "related knowledge perturbation," where subsequent edits interfere with earlier ones. Further analysis reveals that these methods over-rely on subject information, neglecting other critical factors, resulting in reduced editing effectiveness.

Confidence calibration in LLMs, i.e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs. However, current calibration methods for LLMs typically estimate two scalars to represent overall response confidence and correctness, which is inadequate for long-form generation where the response includes multiple atomic facts and may be partially confident and correct. These methods also overlook the relevance of each fact to the query. To address these challenges, we propose a Fact-Level Calibration framework that operates at a finer granularity, calibrating confidence to relevance-weighted correctness at the fact level. Furthermore, comprehensive analysis under the framework inspired the development of Confidence-Guided Fact-level Self-Correction ($\textbf{ConFix}$), which uses high-confidence facts within a response as additional knowledge to improve low-confidence ones. Extensive experiments across four datasets and six models demonstrate that ConFix effectively mitigates hallucinations without requiring external knowledge sources such as retrieval systems.

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered effective solutions to address these challenges. Most recent TDA methods rely on influence functions, assuming the model achieves minimized empirical risk. However, achieving this criterion is difficult, and sourcing accuracy can be compromised by fitting errors during model training. In this paper, we introduce a novel TDA method called Debias and Denoise Attribution (DDA), which enhances influence functions by addressing fitting errors. Specifically, the debias strategy seeks to improve the performance of influence functions by eliminating the knowledge bias present in the base model before fine-tuning, while the denoise strategy aims to reduce discrepancies in influence scores arising from varying degrees of fitting during the training process through smoothing techniques. Experimental results demonstrate that our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. Moreover, DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.

Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment methods fail to transfer the existing safety mechanism for text in LLMs to vision, which leads to vulnerabilities in toxic image. To explore the cause of this problem, we give the insightful explanation of where and how the safety mechanism of LVLMs operates and conduct comparative analysis between text and vision. We find that the hidden states at the specific transformer layers play a crucial role in the successful activation of safety mechanism, while the vision-language alignment at hidden states level in current methods is insufficient. This results in a semantic shift for input images compared to text in hidden states, therefore misleads the safety mechanism. To address this, we propose a novel Text-Guided vision-language Alignment method (TGA) for LVLMs. TGA retrieves the texts related to input vision and uses them to guide the projection of vision into the hidden states space in LLMs. Experiments show that TGA not only successfully transfers the safety mechanism for text in basic LLMs to vision in vision-language alignment for LVLMs without any safety fine-tuning on the visual modality but also maintains the general performance on various vision tasks (Safe and Good). Vision-language alignment methods for Large Vision-Language Models (LVLMs) use a basic LLM, a lightweight vision encoder and projector to efficiently enable the LLM to understand visual input for various vision tasks with relatively low training costs (Liu et al., 2024c; Dai et al., 2023; Zhu et al., 2023). Recent studies indicate the safety of LVLMs deserves attention (Liu et al., 2024a; Wang et al., 2023; Gong et al., 2023). Given that vision and language are aligned into a common space in LVLMs, the safety mechanism should be shared by both of them.

Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. However, existing mainstream TTA methods, predominantly operating at batch level, often exhibit suboptimal performance in complex real-world scenarios, particularly when confronting outliers or mixed distributions. This phenomenon stems from a pronounced over-reliance on statistical patterns over the distinct characteristics of individual instances, resulting in a divergence between the distribution captured by the model and data characteristics. To address this challenge, we propose Meet-In-The-Middle based Test-Time Adaptation ($\textbf{MITA}$), which introduces energy-based optimization to encourage mutual adaptation of the model and data from opposing directions, thereby meeting in the middle. MITA pioneers a significant departure from traditional approaches that focus solely on aligning the model to the data, facilitating a more effective bridging of the gap between model's distribution and data characteristics. Comprehensive experiments with MITA across three distinct scenarios (Outlier, Mixture, and Pure) demonstrate its superior performance over SOTA methods, highlighting its potential to significantly enhance generalizability in practical applications.

With the rapid advancement of large language models (LLMs) for handling complex language tasks, an increasing number of studies are employing LLMs as agents to emulate the sequential decision-making processes of humans often represented as Markov decision-making processes (MDPs). The actions in MDPs adhere to specific probability distributions and require iterative sampling. This arouses curiosity regarding the capacity of LLM agents to comprehend probability distributions, thereby guiding the agent's behavioral decision-making through probabilistic sampling and generating behavioral sequences. To answer the above question, we divide the problem into two main aspects: sequence simulation with known probability distribution and sequence simulation with unknown probability distribution. Our analysis indicates that LLM agents can understand probabilities, but they struggle with probability sampling. Their ability to perform probabilistic sampling can be improved to some extent by integrating coding tools, but this level of sampling precision still makes it difficult to simulate human behavior as agents.