conftrace_

hidden state manipulation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prior regularization (1) representation optimization (1) activation steering (1) greedy decoding (1) neural machine translation (1) chain-of-thought reasoning (1) policy gradient (1)

Papers

Eliciting Chain-of-Thought in Base LLMs via Gradient-Based Representation Optimization AAAI 2026 Trainable Greedy Decoding for Neural Machine Translation EMNLP 2017