Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs Paper • 2311.02262 • Published Nov 3, 2023 • 15
SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference Paper • 2307.02628 • Published Jul 5, 2023 • 10
Explaining black box text modules in natural language with language models Paper • 2305.09863 • Published May 17, 2023 • 2