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: 31 Search mode: keyword Shortlist (0) RSS

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

Top Protocol Hubs

Weekly Eval Paper Digest

The top RLHF, evaluation, and human feedback papers — curated and summarized every Friday.

No spam. Unsubscribe anytime.

Start Here By Objective

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

Scale Your Evaluation Team

Need human evaluators for your benchmark or preference study? OpenTrain sources pre-vetted domain experts into your annotation pipeline.

CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report Evaluation

Mohammed Baharoon, Thibault Heintz, Siavash Raissi, Mahmoud Alabbad, Mona Alhammad, Hassan AlOmaish · Mar 6, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Pairwise Preference Automatic Metrics Medicine
  • We introduce CRIMSON, a clinically grounded evaluation framework for chest X-ray report generation that assesses reports based on diagnostic correctness, contextual relevance, and patient safety.
  • CRIMSON is validated through strong alignment with clinically significant error counts annotated by six board-certified radiologists in ReXVal (Kendalls tau = 0.61-0.71; Pearsons r = 0.71-0.84), and through two additional benchmarks that we…
Open paper
CAMEL: Confidence-Gated Reflection for Reward Modeling

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

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Pairwise PreferenceCritique Edit Automatic Metrics General
  • Building on this insight, we propose CAMEL, a confidence-gated reflection framework that performs a lightweight single-token preference decision first and selectively invokes reflection only for low-confidence instances.
  • Empirically, CAMEL achieves state-of-the-art performance on three widely used reward-model benchmarks with 82.9% average accuracy, surpassing the best prior model by 3.2% and outperforming 70B-parameter models using only 14B parameters,…
Open paper

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Pairwise Preference Long Horizon General
  • Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences.
  • Extensive evaluations on long-horizon benchmarks using the Qwen-3 model family (4B to 32B) validate the effectiveness of TSUBASA, surpassing competitive memory-augmented systems that rely primarily on memory writing, such as Mem0 and…
Open paper
Probing Graph Neural Network Activation Patterns Through Graph Topology

Floriano Tori, Lorenzo Bini, Marco Sorbi, Stéphane Marchand-Maillet, Vincent Ginis · Feb 24, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Pairwise Preference Automatic Metrics General
  • However, it remains unclear how the topology of a graph interacts with the learned preferences of GNNs.
  • Our findings on synthetic graphs and molecular benchmarks reveal that MAs do not preferentially concentrate on curvature extremes, despite their theoretical link to information flow.
Open paper
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang · Feb 13, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Pairwise PreferenceRubric Rating Long Horizon Medicine
  • MedXIAOHE achieves state-of-the-art performance across diverse medical benchmarks and surpasses leading closed-source multimodal systems on multiple capabilities.
  • For medical expert-level reasoning and interaction, MedXIAOHE incorporates diverse medical reasoning patterns via reinforcement learning and tool-augmented agentic training, enabling multi-step diagnostic reasoning with verifiable decision…
Open paper
DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English

Jio Oh, Paul Vicinanza, Thomas Butler, Steven Euijong Whang, Dezhi Hong, Amani Namboori · Jan 30, 2026

Citations: 0

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

Score: 98% High protocol signal Freshness: Cold Status: Ready
Pairwise Preference Human EvalAutomatic Metrics General
  • Human evaluation confirms data quality, with annotators preferring DialectLLM over prior methods in 98.8% of pairwise comparisons for dialect naturalness.
  • Beyond benchmarking, we show that DialectLLM data also serve as a scalable LLM post-training resource, suggesting a practical path toward dialect-aware conversational AI.
Open paper
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia Wu · Mar 4, 2026

Citations: 0

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

Score: 100% High protocol signal Freshness: Warm Status: Fallback
Pairwise Preference Automatic Metrics MathCoding
  • On code generation (LiveCodeBench, CodeContests, SWE-Bench) and math reasoning (AIME, HMMT) benchmarks, V_1-Infer improves Pass@1 by up to 10% over pointwise verification and outperforms recent test-time scaling methods while being…
Open paper
Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment

Junming Liu, Yuqi Li, Shiping Wen, Zhigang Zeng, Tingwen Huang · Mar 7, 2026

Citations: 0

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

Score: 97% Sparse protocol signal Freshness: Warm Status: Fallback
Pairwise Preference General
  • In this paper, we propose Hit-RAG, a multi-stage preference alignment framework designed to resolve these cognitive bottlenecks through a progressive optimization pipeline.
  • Next, Discriminative Preference Alignment enhances robustness against misleading distractors.
Open paper
Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% Moderate protocol signal Freshness: Warm Status: Ready
Pairwise Preference Automatic Metrics General
  • By contrast, zero-shot chain-of-thought on the base Gemma3-1B harms accuracy relative to direct answers, and preference optimization with a simple format+accuracy reward underperforms supervised reasoning.
  • To probe the latter, we introduce GSMClaims and a domain-specialized variant, ThinknCheck-Science, which improves across benchmarks, including 61.0\% accuracy on GSMClaims.
Open paper

Match reason: Matched by broad semantic/index fallback.

Score: 58% High protocol signal Freshness: Warm Status: Ready
Pairwise Preference Automatic Metrics MathLaw
  • We further demonstrate that constructing DPO preference pairs from NSRSA verification teaches the model to distinguish sound from flawed reasoning (reward accuracy 46% to 63%).
Open paper
Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection

Yutong Wang, Xuebo Liu, Derek F. Wong, Zhilin Li, Rongqing Jiang, Min Zhang · May 28, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% Sparse protocol signal Freshness: Hot Status: Fallback
Pairwise Preference CodingMultilingual
  • To address this, we propose a human-like long document translation agent called Loong, which leverages a 3E memory module (Essence-Exemplar-Entity) to store summaries, sentence pairs, and entity records as historical context.
  • Loong optimizes its context policy through reinforcement learning, utilizing preference data derived from its own sampled observe-and-act reasoning trajectories.
Open paper
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency

Aichen Cai, Anmeng Zhang, Anyu Li, Bo Zhang, Bohua Cai, Chang Li · Apr 3, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 55% Moderate protocol signal Freshness: Warm Status: Fallback
Pairwise Preference General
  • JoyAI-LLM Flash is pretrained on a massive corpus of 20 trillion tokens and further optimized through a rigorous post-training pipeline, including supervised fine-tuning (SFT), Direct Preference Optimization (DPO), and large-scale…
Open paper
Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 53% Moderate protocol signal Freshness: Cold Status: Ready
Pairwise PreferenceCritique Edit Human Eval General
  • In this paper, we introduce RebuttalAgent, the first framework to ground academic rebuttal in Theory of Mind (ToM), operationalized through a ToM-Strategy-Response (TSR) framework that models reviewer mental state, formulates persuasion…
  • Extensive experiments show RebuttalAgent significantly outperforms the base model by an average of 18.3% on automated metrics, while also outperforming advanced proprietary models across both automated and human evaluations.
Open paper
HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue

Laya Iyer, Kriti Aggarwal, Sanmi Koyejo, Gail Heyman, Desmond C. Ong, Subhabrata Mukherjee · Jan 9, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 53% Moderate protocol signal Freshness: Cold Status: Ready
Pairwise PreferenceRubric Rating Human EvalLlm As Judge General
  • Despite rapid progress in language models, we still lack a clear way to understand how their abilities in these interpersonal domains compare to those of humans.
  • We introduce HEART, the first-ever framework that directly compares humans and LLMs on the same multi-turn emotional-support conversations.
Open paper

Match reason: Matched by broad semantic/index fallback.

Score: 52% Sparse protocol signal Freshness: Warm Status: Fallback
Pairwise Preference General
  • To address this issue, we propose Multi-Faceted Self-Consistent Preference Aligned CQR (MSPA-CQR).
  • Then we propose prefix guided multi-faceted direct preference optimization to learn preference information from three different dimensions.
Open paper
Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 52% Sparse protocol signal Freshness: Warm Status: Fallback
Pairwise PreferenceDemonstrations General
  • Experiments across a variety of steering tasks and benchmarks demonstrate that COLD-Steer achieves upto 95% steering effectiveness while using 50 times fewer samples compared to the best baseline.
  • Our framework opens new possibilities for adaptive, context-aware model control that can flexibly address varying loss-driven human preferences through principled approximation of learning dynamics rather than specialized training…
Open paper
From Static Benchmarks to Dynamic Protocol: Agent-Centric Text Anomaly Detection for Evaluating LLM Reasoning

Seungdong Yoa, Sanghyu Yoon, Suhee Yoon, Dongmin Kim, Ye Seul Sim, Junhyun Lee · Feb 27, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 52% Sparse protocol signal Freshness: Warm Status: Fallback
Pairwise Preference General
  • To overcome these limitations, we propose an agent-centric benchmarking paradigm that moves beyond static datasets by introducing a dynamic protocol in which autonomous agents iteratively generate, validate, and solve problems.
  • Adopting text anomaly detection as our primary evaluation format, which demands cross-sentence logical inference and resists pattern-matching shortcuts, we demonstrate that this protocol systematically exposes corner-case reasoning errors…
Open paper
Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation

Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao, Fuli Feng, Xiangnan He · Dec 7, 2025

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 46% Sparse protocol signal Freshness: Cold Status: Fallback
Pairwise Preference Coding
  • Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlooking individual users.
  • Personalization is essential, yet early approaches-such as prompt customization or fine-tuning-struggle to reason over implicit preferences, limiting real-world effectiveness.
Open paper

Protocol Hubs

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.