activity
20242026
most citedMemory Injection Attacks on LLM Agents via Query-Only Interaction

1 citations · 1 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Retrieval Heads are Dynamic

Yuping Lin, Zitao Li, Yue Xing +6

Recent studies have identified "retrieval heads" in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on st…

cs.CL2025

Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?

Yang Nan, Pengfei He, Ravi Tandon +1

Large language models (LLMs) have delivered significant breakthroughs across diverse domains but can still produce unreliable or misleading outputs, posing critical challenges for…

cs.CL2025

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

Shenglai Zeng, Pengfei He, Kai Guo +4

Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend…

cs.CL2025

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

Yingqian Cui, Pengfei He, Jingying Zeng +11

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 c…

cs.CL2024

Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis

Yuping Lin, Pengfei He, Han Xu +4

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack…

cs.CL2024

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

Yingqian Cui, Pengfei He, Xianfeng Tang +4

Few-shot Chain-of-Thought (CoT) prompting has demonstrated strong performance in improving the reasoning capabilities of large language models (LLMs). While theoretical investigati…