A General Framework to Enhance Fine-tuning-based LLM Unlearning

Unlearning has been proposed to remove copyrighted and privacy-sensitive data from Large Language Models (LLMs). Existing approaches primarily rely on fine-tuning-based methods, which can be categorized into gradient ascent-based (GA-based) and suppression-based methods. However, they often degrade model utility (the ability to respond to normal prompts). In this work, we aim to develop a general framework that enhances the utility of fine-tuning-based unlearning methods. To achieve this goal, we first investigate the common property between GA-based and suppression-based methods. We unveil that GA-based methods unlearn by distinguishing the target data (i.e., the data to be removed) and suppressing related generations, which is essentially the same strategy employed by suppression-based methods. Inspired by this finding, we introduce Gated Representation UNlearning (GRUN) which has two components: a soft gate function for distinguishing target data and a suppression module using Representation Fine-tuning (ReFT) to adjust representations rather than model parameters. Experiments show that GRUN significantly improves the unlearning and utility. Meanwhile, it is general for fine-tuning-based methods, efficient and promising for sequential unlearning.

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach

Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend to over-rely on external knowledge, making them vulnerable to misleading and unhelpful contexts. To address this, we propose the concept of context-robust LLMs, which can effectively balance internal knowledge with external context, similar to human cognitive processes. Specifically, context-robust LLMs should rely on external context only when lacking internal knowledge, identify contradictions between internal and external knowledge, and disregard unhelpful contexts. To achieve this goal, we introduce Grft, a lightweight and plug-and-play gated representation fine-tuning approach. Grft consists of two key components: a gating mechanism to detect and filter problematic inputs, and low-rank representation adapters to adjust hidden representations. By training a lightweight intervention function with only 0.0004\% of model size on fewer than 200 examples, Grft can effectively adapt LLMs towards context-robust behaviors.

Multi-Faceted Studies on Data Poisoning can Advance LLM Development

The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and varied inference methods. While prior research on data poisoning attacks has primarily focused on the safety vulnerabilities of LLMs, these attacks face significant challenges in practice. Secure data collection, rigorous data cleaning, and the multistage nature of LLM training make it difficult to inject poisoned data or reliably influence LLM behavior as intended. Given these challenges, this position paper proposes rethinking the role of data poisoning and argue that multi-faceted studies on data poisoning can advance LLM development. From a threat perspective, practical strategies for data poisoning attacks can help evaluate and address real safety risks to LLMs. From a trustworthiness perspective, data poisoning can be leveraged to build more robust LLMs by uncovering and mitigating hidden biases, harmful outputs, and hallucinations. Moreover, from a mechanism perspective, data poisoning can provide valuable insights into LLMs, particularly the interplay between data and model behavior, driving a deeper understanding of their underlying mechanisms.

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models

Chain-of-Thought (CoT) reasoning, which breaks down complex tasks into intermediate reasoning steps, has significantly enhanced the performance of large language models (LLMs) on challenging tasks. However, the detailed reasoning process in CoT often incurs long generation times and high computational costs, partly due to the inclusion of unnecessary steps. To address this, we propose a method to identify critical reasoning steps using perplexity as a measure of their importance: a step is deemed critical if its removal causes a significant increase in perplexity. Our method enables models to focus solely on generating these critical steps. This can be achieved through two approaches: refining demonstration examples in few-shot CoT or fine-tuning the model using selected examples that include only critical steps. Comprehensive experiments validate the effectiveness of our method, which achieves a better balance between the reasoning accuracy and efficiency of CoT.

Unveiling Privacy Risks in LLM Agent Memory

Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions in the memory module for demonstrations, introducing new privacy risks for LLM agents. In this work, we systematically investigate the vulnerability of LLM agents to our proposed Memory EXTRaction Attack (MEXTRA) under a black-box setting. To extract private information from memory, we propose an effective attacking prompt design and an automated prompt generation method based on different levels of knowledge about the LLM agent. Experiments on two representative agents demonstrate the effectiveness of MEXTRA. Moreover, we explore key factors influencing memory leakage from both the agent's and the attacker's perspectives. Our findings highlight the urgent need for effective memory safeguards in LLM agent design and deployment.

Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective

Retrieval-Augmented Generation (RAG) systems have shown promise in enhancing the performance of Large Language Models (LLMs). However, these systems face challenges in effectively integrating external knowledge with the LLM's internal knowledge, often leading to issues with misleading or unhelpful information. This work aims to provide a systematic study on knowledge checking in RAG systems. We conduct a comprehensive analysis of LLM representation behaviors and demonstrate the significance of using representations in knowledge checking. Motivated by the findings, we further develop representation-based classifiers for knowledge filtering. We show substantial improvements in RAG performance, even when dealing with noisy knowledge databases. Our study provides new insights into leveraging LLM representations for enhancing the reliability and effectiveness of RAG systems.

A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration

Few-shot Chain-of-Thought (CoT) prompting has demonstrated strong performance in improving the reasoning capabilities of large language models (LLMs). While theoretical investigations have been conducted to understand CoT, the underlying transformer used in these studies isolates the CoT reasoning process into separated in-context learning steps (Stepwise ICL). In this work, we theoretically show that, compared to Stepwise ICL, the transformer gains better error correction ability and more accurate predictions if the reasoning from earlier steps (Coherent CoT) is integrated. Given that this coherent reasoning changes the behavior of the transformer, we further investigate the sensitivity of the transformer with Coherent CoT when the demonstration examples are corrupted at the inference stage. Our theoretical results indicate that the transformer is more sensitive to errors in intermediate reasoning steps than the final outcome. Building upon this observation, we propose an improvement on CoT by incorporating both correct and incorrect reasoning paths in the demonstration. Our experiments validate the effectiveness of the proposed approach.

Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning

Zero-shot reasoning methods with Large Language Models (LLMs) offer significant advantages including great generalization to novel tasks and reduced dependency on human-crafted examples. However, the current zero-shot methods still have limitations in complex tasks, e.g., answering questions that require multi-step reasoning. In this paper, we address this limitation by introducing a novel structure-oriented analysis method to help LLMs better understand the question and guide the problem-solving process of LLMs. We first demonstrate how the existing reasoning strategies, Chain-of-Thought and ReAct, can benefit from our structure-oriented analysis. In addition to empirical investigations, we leverage the probabilistic graphical model to theoretically explain why our structure-oriented analysis can improve the LLM reasoning process. To further improve the reliability in complex question-answering tasks, we propose a multi-agent reasoning system, Structure-oriented Autonomous Reasoning Agents (SARA), that can better enforce the reasoning process following our structure-oriented analysis by refinement techniques and is equipped with external knowledge retrieval capability to reduce factual errors. Extensive experiments verify the effectiveness of the proposed reasoning system. Surprisingly, in some cases, the system even surpasses few-shot methods. Finally, the system not only improves reasoning accuracy in complex tasks but also demonstrates robustness against potential attacks that corrupt the reasoning process.

Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models

Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their success. However, concerns have been raised about the unauthorized use of copyrighted materials and potential copyright infringement. Existing methods, such as sample-level Membership Inference Attacks (MIA) and distribution-based dataset inference, distinguish member data (data used for training) and non-member data by leveraging the common observation that models tend to memorize and show greater confidence in member data. Nevertheless, these methods face challenges when applied to LLMs and VLMs, such as the requirement for ground-truth member data or non-member data that shares the same distribution as the test data. In this paper, we propose a novel dataset-level membership inference method based on Self-Comparison. We find that a member prefix followed by a non-member suffix (paraphrased from a member suffix) can further trigger the model's memorization on training data. Instead of directly comparing member and non-member data, we introduce paraphrasing to the second half of the sequence and evaluate how the likelihood changes before and after paraphrasing. Unlike prior approaches, our method does not require access to ground-truth member data or non-member data in identical distribution, making it more practical. Extensive experiments demonstrate that our proposed method outperforms traditional MIA and dataset inference techniques across various datasets and models, including including public models, fine-tuned models, and API-based commercial models.

Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study

In-context learning (ICL) has emerged as a powerful capability for large language models (LLMs) to adapt to downstream tasks by leveraging a few (demonstration) examples. Despite its effectiveness, the mechanism behind ICL remains underexplored. To better understand how ICL integrates the examples with the knowledge learned by the LLM during pre-training (i.e., pre-training knowledge) and how the examples impact ICL, this paper conducts a theoretical study in binary classification tasks. In particular, we introduce a probabilistic model extending from the Gaussian mixture model to exactly quantify the impact of pre-training knowledge, label frequency, and label noise on the prediction accuracy. Based on our analysis, when the pre-training knowledge contradicts the knowledge in the examples, whether ICL prediction relies more on the pre-training knowledge or the examples depends on the number of examples. In addition, the label frequency and label noise of the examples both affect the accuracy of the ICL prediction, where the minor class has a lower accuracy, and how the label noise impacts the accuracy is determined by the specific noise level of the two classes. Extensive simulations are conducted to verify the correctness of the theoretical results, and real-data experiments also align with the theoretical insights. Our work reveals the role of pre-training knowledge and examples in ICL, offering a deeper understanding of LLMs' behaviors in classification tasks.