ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
arXiv:2502.15543v4 Announce Type: replace Abstract: Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external…
Read the full articleYou might also wanna read
LiveBrowseComp reveals LLM search agents rely on memorized knowledge, not genuine web searching
Are LLM-based search agents genuinely searching, or using the web to verify what they already know? We study this question on BrowseComp wit
arxiv.org·1mo ago
PRECISE: A Statistical Framework for Reducing LLM Bias in Search and Ranking Evaluations
Evaluating the quality of search, ranking and RAG systems traditionally requires a significant number of human relevance annotations. In rec
arxiv.org·1mo ago
Expected Attention: KV Cache Compression Method for Efficient LLM Inference
Memory consumption of the Key-Value (KV) cache represents a major bottleneck for efficient large language model inference. While attention-s
arxiv.org·9mo ago
Research Reveals LLM Refusal Behavior Is Controlled by a Single Direction in Model Activations
Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests
arXiv.org·2mo ago
Training Large Language Models for Honesty Through Self-Reported Confessions
Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidenc
arxiv.org·6mo ago
Deployment-Time Memorization in Foundation-Model Agents: Privacy-Utility Tradeoffs in Persistent Memory Systems
Foundation-model agents are increasingly long-lived systems that remember users across interactions, making memorization an explicit deploym
arxiv.org·25d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.