conftrace_

post-training alignment

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) inference-time alignment (1) best-of-n decoding (1) speculative rejection (1) sentiment distribution (1) multi-perspective fusion (1) audience design (1) reward model (1) language model (1) bias mitigation (1)

Papers

An Information-Theoretic Study of RLHF-Induced Uniformity in Large Language Model Outputs CoNLL 2026 MPF: Aligning and Debiasing Language Models post Deployment via Multi-Perspective Fusion IJCNLP 2025 Fast Best-of-N Decoding via Speculative Rejection NeurIPS 2024