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: 78 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.

State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

Navan Preet Singh, Anurag Garikipati, Ahmed Abulkhair, Jyani Akshay Jagdishbhai, Atul Yaduvanshi, Amarendra Chaudhary · Apr 7, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Demonstrations Automatic Metrics General
  • Arabic-DeepSeek-R1 achieves the highest average score across the seven-benchmark OALL suite while establishing SOTA or near-SOTA, including dominant results on grammar-focused MadinahQA (surpassing both GPT-5.1 and the OALL leader by…
  • Our results indicate that the combination of sparse MoE architecture, culturally-informed CoT distillation with explicit Arabic linguistic checks, and strategic bilingual data curation enables an open-source adapted model to systematically…
Open paper
Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning

Navan Preet Singh, Xiaokun Wang, Anurag Garikipati, Madalina Ciobanu, Qingqing Mao, Ritankar Das · Apr 7, 2026

Citations: 0

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Ready
Expert Verification Automatic Metrics General
  • These models remarkably achieve high enough accuracy on the Cross-Domain Pedagogical Knowledge (CDPK) Benchmark to establish new state-of-the-art (SOTA) results across the interactive Pedagogy Benchmark Leaderboard and surpass significantly…
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

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

Score: 100% Moderate protocol signal Freshness: Warm Status: Fallback
Llm As JudgeAutomatic Metrics General
  • We evaluate on HotpotQA-RAG v3, a controlled multi-hop benchmark, under an artifact-aware protocol (shortcut baselines, counterfactual swaps, no-oracle checks, GPT-4o audits).
  • Calibrated SURE-RAG reaches 0.9075 Macro-F1 (0.8951 +/- 0.0069), substantially above DeBERTa mean-pooling (0.6516) and a GPT-4o judge (0.7284), while matching a strong but opaque concat cross-encoder (0.8888 +/- 0.0109) with full…
Open paper
Citations: 0

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

Score: 100% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Tool Use General
  • We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use.
  • Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains.
Open paper
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen · Apr 8, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% High protocol signal Freshness: Warm Status: Ready
Red Team Automatic Metrics Long Horizon General
  • As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.
  • To address this gap, we introduce TraceSafe-Bench, the first comprehensive benchmark specifically designed to assess mid-trajectory safety.
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
Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade, Manuel R. Ciosici, Yizhe Zhang, Irina Belousova · May 8, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon General
  • Each training trajectory is built through a chain of blind stochastic jumps with no evaluation of sequence quality; a single bad decision at an early midpoint propagates through subsequent steps, yet the student must imitate the result.
Open paper
Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon General
  • Agentic RAG extends this paradigm by replacing single-step retrieval with a multi-step process, in which the large language model (LLM) acts as a search agent that generates intermediate thoughts and subqueries to iteratively interact with…
  • Extensive experiments on seven benchmark datasets show that LatentRAG achieves performance comparable to explicit agentic RAG methods while reducing inference latency by approximately 90%, substantially narrowing the latency gap with…
Open paper
Material Database Agent: A Multimodal Agentic Framework for Scientific Literature Mining

Achuth Chandrasekhar, Omid Barati Farimani, Radheesh Sharma Meda, Amir Barati Farimani · May 5, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Multi Agent General
  • Material Database Agent (MDA) is a modular, multi-agent system architecture for converting research literature into structured databases.
  • Multiple sub-agents read these markdown files and figures in parallel to assemble sub-databases for each paper.
Open paper
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Zhengxu Yu, Yu Fu, Zhiyuan He, Yuxuan Huang, Lee Ka Yiu, Meng Fang · Apr 24, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Multi Agent General
  • Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning.
  • To fill this gap, we introduce OneManCompany (OMC), a framework that elevates multi-agent systems to the organisational level.
Open paper
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents

Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel, Neel Patel, Majid Fekri, Tara Khani · Apr 23, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon General
  • The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems.
  • Through systematic benchmarking on the LongMemEval and LoCoMo evaluation suites, Memanto achieves state of the art accuracy scores of 89.8 percent and 87.1 percent respectively.
Open paper
Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions

Pengcheng Lyu, Chaokun Zhang, Gong Chen, Tao Tang, Zhaoxiang Luo · Apr 2, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 58% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Multi Agent General
  • Multi-agent collaborative perception enables autonomous systems to overcome individual sensing limits through collective intelligence.
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
Learning-augmented robotic automation for real-world manufacturing

Yunho Kim, Quan Nguyen, Taewhan Kim, Youngjin Heo, Joonho Lee · Apr 24, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 52% Sparse protocol signal Freshness: Warm Status: Fallback
Demonstrations General
  • Here we present Learning-Augmented Robotic Automation, a hybrid system that integrates learned task controllers and a neural 3D safety monitor into conventional industrial workflows.
  • We deployed the system on an electric-motor production line to automate deformable cable insertion and soldering under real manufacturing constraints, a step previously performed manually by human workers.
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

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.