conftrace_

attention modification

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

interpretability research (1) mechanism competition (1) logit inspection (1) credibility scoring (1) large language model (1) mechanism analysis (1) llm safety (1) jailbreak defense (1) retrieval-augmented generation (1) language model (1)

Papers

CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG AAAI 2025 DeTAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification ACL 2025 Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals ACL 2024