conftrace_

model truthfulness

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

language model truthfulness (1) activation intervention (1) hidden activation (1) large language model (1) model steering (1) inference-time intervention (1) low-rank mapping (1) hallucination detection (1) low-rank adaptation (1) knowledge graph (1)

Papers

KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge EACL 2026 Probe-Free Low-Rank Activation Intervention NAACL 2025