conftrace_

lookback ratio

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

classifier-guided decoding (1) cross-model transfer (1) large language model (1) contextual hallucination (1) attention map (1) hallucination detection (1)

Papers

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps EMNLP 2024