Skip to content

Researcher Tools

Human Feedback and Eval Paper Explorer

A focused feed for RLHF, preference data, rater protocols, agent evaluation, and LLM-as-judge research. Every paper includes structured metadata for quick triage.

Total papers: 3 Search mode: keyword Shortlist (0) RSS

Filter by tag

All Automatic Metrics (631) General (245) Long Horizon (128) Pairwise Preference (128) Coding (97) Simulation Env (86) Multi Agent (63) Medicine (42) Expert Verification (41) Llm As Judge (40) Web Browsing (35) Rubric Rating (33) Demonstrations (31) Human Eval (30) Red Team (30) Math (29)

Featured Papers

Popular high-signal papers with direct links to full protocol pages.

Browse by Topic

Jump directly into tag and hub pages to crawl deeper content clusters.

Popular Tags

Automatic Metrics (631) General (245) Long Horizon (128) Pairwise Preference (128) Coding (97) Simulation Env (86) Multi Agent (63) Medicine (42) Expert Verification (41) Llm As Judge (40) Web Browsing (35) Rubric Rating (33)

Top Protocol Hubs

Start Here By Objective

Pick your immediate research objective and jump directly to high-signal pages, not generic search.

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Fallback
Pairwise Preference Coding
  • To bridge this gap, we propose Meta-Weighted Adaptive Preference Optimization (MetaAPO), a novel framework that dynamically couples data generation with model training.
  • Experiments on AlpacaEval 2, Arena-Hard and MT-Bench demonstrate that MetaAPO consistently outperforms existing preference optimization approaches across various settings, while reducing 42% in online annotation costs.
Open paper
Less is More: Improving LLM Alignment via Preference Data Selection

Xun Deng, Han Zhong, Rui Ai, Fuli Feng, Zheng Wang, Xiangnan He · Feb 20, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Fallback
Pairwise Preference General
  • Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences.
  • To further mitigate the noise in different reward models, we propose a Bayesian Aggregation approach that unifies multiple margin sources (external and implicit) into a single preference probability.
Open paper
Revisiting Self-Play Preference Optimization: On the Role of Prompt Difficulty

Yao Xiao, Jung-jae Kim, Roy Ka-wei Lee, Lidong Bing · Oct 7, 2025

Citations: 0

Match reason: Keyword overlap 1/1 across title and protocol fields.

Score: 75% Moderate protocol signal Freshness: Cold Status: Fallback
Pairwise Preference General
  • Self-play preference optimization has emerged as a prominent paradigm for aligning large language models (LLMs).
  • It typically involves a language model to generate on-policy responses for prompts and a reward model (RM) to guide the selection of chosen and rejected responses, which can be further trained with direct preference optimization (DPO).
Open paper

Protocol Hubs

Expert Verification Papers (39) CS.CL + Expert Verification Papers (30) Rubric Rating Papers (29) CS.CL + Rubric Rating Papers (27) CS.AI + Expert Verification Papers (25) Pairwise Preference Papers (114) CS.CL + Pairwise Preference Papers (99) Coding Papers (91) CS.CL Human Feedback And Eval Papers (1,674) CS.CL + Coding Papers (73) Expert Verification Papers (Last 120 Days) (30) Medicine + Expert Verification Papers (20) Expert Verification Papers (Last 90 Days) (29) Medicine Papers (40) CS.AI + Medicine Papers (25) Automatic Metrics + Expert Verification Papers (25)

Benchmark Hubs

Metric Hubs

Daily Archives

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote