conftrace_

token-wise analysis

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

factual decoding (1) attribution analysis (1) token matching (1) large language model (1) cross-layer entropy (1) hidden-state prediction (1) fine-tuned transformer (1) passage reranking (1) positional bia (1) decoding method (1)

Papers

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models NAACL 2025 How Does BERT Rerank Passages? An Attribution Analysis with Information Bottlenecks EMNLP 2021