Skip to content

OpenTrain Research 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: 277 Search mode: keyword RSS

Filter by tag

All Automatic Metrics (876) General (528) Coding (281) Simulation Env (109) Multilingual (92) Math (90) Long Horizon (74) Medicine (69) Pairwise Preference (64) Law (43) Multi Agent (38) Human Eval (36) Expert Verification (23) Red Team (21) Web Browsing (21) Critique Edit (19)
Overton Pluralistic Reinforcement Learning for Large Language Models

Yu Fu, Seongho Son, Ilija Bogunovic · Feb 24, 2026

Citations: 0
Llm As JudgeAutomatic Metrics General
  • Existing alignment paradigms remain limited in capturing the pluralistic nature of human values.
  • First, similarity estimator training fine-tunes a Sentence Transformer for Overton Pluralism tasks to provide more accurate coverage evaluation of generated responses.
PyVision-RL: Forging Open Agentic Vision Models via RL

Shitian Zhao, Shaoheng Lin, Ming Li, Haoquan Zhang, Wenshuo Peng, Kaipeng Zhang · Feb 24, 2026

Citations: 0
Automatic Metrics Tool Use General
  • Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior.
  • Experiments show strong performance and improved efficiency, demonstrating that sustained interaction and on-demand visual processing are critical for scalable multimodal agents.
Citations: 0
Pairwise PreferenceRlaif Or Synthetic Feedback Human Eval General
  • Preference-based RL offers an appealing alternative by learning from human preferences over pairs of behavioural outcomes.
  • More recently, RL from AI feedback (RLAIF) has demonstrated that large language models (LLMs) can generate preference labels at scale, mitigating the reliance on human annotators.
ToolMATH: A Math Tool Benchmark for Realistic Long-Horizon Multi-Tool Reasoning

Hyeonje Choi, Jeongsoo Lee, Hyojun Lee, Jay-Yoon Lee · Feb 24, 2026

Citations: 0
Simulation Env Long Horizon Math
  • We introduce \ToolMATH, a math-grounded benchmark that evaluates tool-augmented language models in realistic multi-tool environments where the output depends on calling schema-specified tools and sustaining multi-step execution.
  • It turns math problems into a controlled, correctness-checkable benchmark with tool sets, enabling systematic evaluation of model reliability under (1) large, overlapping tool catalogs and (2) the absence of the intended capability.
ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

Che Wang, Fuyao Zhang, Jiaming Zhang, Ziqi Zhang, Yinghui Wang, Longtao Huang · Feb 24, 2026

Citations: 0
Automatic Metrics Long Horizon General
  • Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution.
  • Existing defenses typically rely on strict filtering or refusal mechanisms, which suffer from a critical limitation: over-refusal, prematurely terminating valid agentic workflows.
CAMEL: Confidence-Gated Reflection for Reward Modeling

Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar, Kun Xu · Feb 24, 2026

Citations: 0
Pairwise PreferenceCritique Edit Automatic Metrics General
  • Reward models play a fundamental role in aligning large language models with human preferences.
  • Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and generative judging models, which offer richer reasoning at the cost of higher computational ove
Citations: 0
Human EvalAutomatic Metrics General
  • Experiments show that CARE outperforms leading LLMs and substantially reduces the gap between counselor evaluations and client-perceived alliance, achieving over 70% higher Pearson correlation with client ratings.
  • CARE also produces high-quality, contextually grounded rationales, validated by both automatic and human evaluations.
GATES: Self-Distillation under Privileged Context with Consensus Gating

Alex Stein, Furong Huang, Tom Goldstein · Feb 24, 2026

Citations: 0
Automatic Metrics Long Horizon Math
  • Held-out in-domain accuracy under asymmetric evaluation improves from 46.0\% to 62.0\%, and average (maj@8) accuracy on public document-free math benchmarks improves from 20.2\% to 35.4\%.
Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning

Justin Lovelace, Christian Belardi, Sofian Zalouk, Adhitya Polavaram, Srivatsa Kundurthy, Kilian Q. Weinberger · Feb 24, 2026

Citations: 0
Llm As JudgeAutomatic Metrics General
  • Evaluations show STAR-LDM significantly outperforms similar-sized models on language understanding benchmarks and achieves $>70\%$ win rates in LLM-as-judge comparisons for narrative coherence and commonsense reasoning.
Citations: 0
Demonstrations Automatic Metrics Multi Agent Coding
  • Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts.
  • Imitation learning has emerged as one of the prominent approaches to build such agents by training them to mimic human-demonstrated behaviors.
PreScience: A Benchmark for Forecasting Scientific Contributions

Anirudh Ajith, Amanpreet Singh, Jay DeYoung, Nadav Kunievsky, Austin C. Kozlowski, Oyvind Tafjord · Feb 24, 2026

Citations: 0
Human EvalSimulation Env General
  • We introduce PreScience -- a scientific forecasting benchmark that decomposes the research process into four interdependent generative tasks: collaborator prediction, prior work selection, contribution generation, and impact prediction.
  • We develop baselines and evaluations for each task, including LACERScore, a novel LLM-based measure of contribution similarity that outperforms previous metrics and approximates inter-annotator agreement.
An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models

Cathy Shyr, Yan Hu, Rory J. Tinker, Thomas A. Cassini, Kevin W. Byram, Rizwan Hamid · Feb 23, 2026

Citations: 0
Expert Verification Automatic Metrics Medicine
  • Existing artificial intelligence approaches typically optimize individual components of phenotyping but do not operationalize the full clinical workflow of extracting features from clinical text, standardizing them to Human Phenotype Ontolo
  • Using clinician-curated HPO terms as the gold standard, RARE-PHENIX consistently outperformed a state-of-the-art deep learning baseline (PhenoBERT) across ontology-based similarity and precision-recall-F1 metrics in end-to-end evaluation (i
gencat: Generative computerized adaptive testing

Wanyong Feng, Andrew Lan · Feb 23, 2026

Citations: 0
Pairwise Preference Automatic Metrics Coding
  • We train the model in a two-step process, first via Supervised Fine-Tuning and then via preference optimization for knowledge-response alignment.
Contextual Safety Reasoning and Grounding for Open-World Robots

Zachary Ravichandran, David Snyder, Alexander Robey, Hamed Hassani, Vijay Kumar, George J. Pappas · Feb 23, 2026

Citations: 0
Simulation Env Web Browsing General
  • Traditional safety approaches enforce fixed constraints in user-specified contexts, limiting their ability to handle the open-ended contextual variability of real-world deployment.
  • We address this gap via CORE, a safety framework that enables online contextual reasoning, grounding, and enforcement without prior knowledge of the environment (e.g., maps or safety specifications).
Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teaming

Ian Steenstra, Paola Pedrelli, Weiyan Shi, Stacy Marsella, Timothy W. Bickmore · Feb 23, 2026

Citations: 0
Red Team Simulation Env Medicine
  • Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue.
  • We introduce an evaluation framework that pairs AI psychotherapists with simulated patient agents equipped with dynamic cognitive-affective models and assesses therapy session simulations against a comprehensive quality of care and risk ont

Protocol Hubs

Simulation Env Papers (109) Multilingual Papers (92) Math Papers (90) Automatic Metrics Papers (876) General Papers (528) Coding Papers (281) Long Horizon Papers (74) Medicine Papers (69) Automatic Metrics + Long Horizon Papers (55) Pairwise Preference Papers (64) Automatic Metrics + Pairwise Preference Papers (51) Law Papers (43) Multi Agent Papers (38) Human Eval Papers (36) Automatic Metrics + Multi Agent Papers (25) Simulation Env + Long Horizon Papers (20)

Benchmark Hubs

Metric Hubs

Daily Archives