AI Paper Atlas

Research map / Large language models / Alignment and preferences

Reliability-Aware LLM Alignment from Inconsistent Human Feedback

Jingyi Huang, Ruohan Zong, Yujun Feng, Liran Ma, Lanyu Shang, Yang Zhang

ICML 2026 · Large language models › Alignment and preferences · approach: Active and token-level preference learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add RGPODPO · MultiPref (Llama-3-8B-Instruct)Arena-Hard win rate: 43.70% to 46.60%Improved
add RGPOIPO · MultiPref (Llama-3-8B-Instruct)Arena-Hard win rate: 51.90% to 53.10%Improved
add RGPOSimPO · MultiPref (Qwen2.5-7B-Instruct)AlpacaEval 2 raw win rate: 69.07 -> 85.36Improved
add RGPOSimPO · HelpSteer2-Disagreement (Llama-3-8B-Instruct)AlpacaEval 2 raw win rate: 12.31 -> 25.60Improved
add RGPODPO · HelpSteer2-Disagreement (Qwen2.5-7B-Instruct)AlpacaEval 2 raw win rate: 40.31 -> 39.83No clear effect
add RGPODPO · MultiPref (Qwen2.5-7B-Instruct)Arena-Hard win rate: 78.20 -> 77.10Hurt
add ILRE (iterative latent reliability estimation) (ablation)RGPO-DPO · MultiPref (Llama-3-8B-Instruct)Arena-Hard win rate: 42.50 -> 46.60Improved
add RACO (reliability-aware consistency optimization) (ablation)RGPO-DPO · MultiPref (Llama-3-8B-Instruct)Arena-Hard win rate: 45.40 -> 46.60Improved
replace confidence filtering with RGPO (ablation)DPO · MultiPref (Llama-3-8B-Instruct)AlpacaEval 2 raw win rate: 38.67 -> 40.74Improved
add confidence filtering (ablation)DPO · MultiPref (Llama-3-8B-Instruct)AlpacaEval 2 LC win rate: 35.55 -> 36.08Mixed
add Tanh scaling of consistency weight (ablation)RGPO-DPO · MultiPref (Llama-3-8B-Instruct)AlpacaEval 2 LC win rate: 35.54 -> 38.30Improved
RGPO ILRE yields more tie labels than uniform ensemble (ablation)preference construction · MultiPreftie fraction: 12.27% to 29.03%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy