15 papers
Evaluating the Reversal Curse in Model Editing
Hao-Xiang Xu, Jun-Yu Ma, Zhen-Hua Ling +3
Large language models (LLMs) are prone to hallucinate unintended text due to false or outdated knowledge. Since retraining LLMs is resource intensive, there has been a growing inte…
Energy-Regularized Sequential Model Editing on Hyperspheres
Qingyuan Liu, Jia-Chen Gu, Yunzhi Yao +2
Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alternative to retraining, but sequen…
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
Di Wu, Zixiang Ji, Asmi Kawatkar +4
Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure m…
BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
Jia-Chen Gu, Junyi Zhang, Di Wu +3
As retrieval-augmented generation (RAG) tackles complex tasks, increasingly expanded contexts offer richer information, but at the cost of higher latency and increased cognitive lo…
Constraining Sequential Model Editing with Editing Anchor Compression
Hao-Xiang Xu, Jun-Yu Ma, Zhen-Hua Ling +2
Large language models (LLMs) struggle with hallucinations due to false or outdated knowledge. Given the high resource demands of retraining these models, there is an increasing foc…
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
Xiaojie Gu, Ziying Huang, Jia-Chen Gu +1
Lifelong learning enables large language models (LLMs) to adapt to evolving information by continually updating their internal knowledge. An ideal system should support efficient,…