7 papers
Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence
Wanying Ren, Xin Song, Futing Wang +2
Parameter-based knowledge editing updates the internal knowledge of large language models (LLMs) via localized weight modifications and has attracted significant attention. However…
Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents
Xinze Li, Yuhang Zang, Yixin Cao +1
Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We obse…
Can LLM Safety Be Ensured by Constraining Parameter Regions?
Zongmin Li, Jian Su, Farah Benamara +1
Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic e…
Demystifying the Slash Pattern in Attention: The Role of RoPE
Yuan Cheng, Fengzhuo Zhang, Yunlong Hou +5
Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the -th sub-diagonal for some offset . These patterns play a k…
EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents
Xinze Li, Ziyue Zhu, Siyuan Liu +4
We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generate…
Benchmarking and Rethinking Knowledge Editing for Large Language Models
Guoxiu He, Xin Song, Futing Wang +1
Knowledge editing aims to update the embedded knowledge within Large Language Models (LLMs). However, existing approaches, whether through parameter modification or external memory…