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: 592 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.

Stealth Fine-Tuning: Efficiently Breaking Alignment in RVLMs Using Self-Generated CoT

Le Yu, Zhengyue Zhao, Yawen Zheng, Yunhao Liu · Nov 18, 2025

Citations: 0

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

Score: 78% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • Reasoning-augmented Vision-Language Models (RVLMs) rely on safety alignment to prevent harmful behavior, yet their exposed chain-of-thought (CoT) traces introduce new attack surfaces.
  • In this work, we find that the safety alignment of RVLMs can be easily broken through a novel attack method termed Stealth Fine-Tuning.
Open paper
Conformal Constrained Policy Optimization for Cost-Effective LLM Agents

Wenwen Si, Sooyong Jang, Insup Lee, Osbert Bastani · Nov 14, 2025

Citations: 0

Match reason: Title directly matches "cost".

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • We propose a novel strategy where we combine multiple LLM models with varying cost/accuracy tradeoffs in an agentic manner, where models and tools are run in sequence as determined by an orchestration model to minimize cost subject to a…
  • Across two multi-hop question answering benchmarks, CCPO achieves up to a 30% cost reduction compared to other cost-aware baselines and LLM-guided methods without compromising reliability.
Open paper
From Efficiency to Adaptivity: A Deeper Look at Adaptive Reasoning in Large Language Models

Chao Wu, Baoheng Li, Mingchen Gao, Yu Tian, Zhenyi Wang · Nov 13, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • Recent advances in large language models (LLMs) have made reasoning a central benchmark for evaluating intelligence.
  • We conclude by identifying open challenges in self-evaluation, meta-reasoning, and human-aligned reasoning control.
Open paper
iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification

Zixun Xiong, Gaoyi Wu, Qingyang Yu, Mingyu Derek Ma, Lingfeng Yao, Miao Pan · Nov 12, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • A distinctive feature of information capacity is its incorporation of tokenizer efficiency, which affects inference costs but is often neglected in LLM evaluations.
  • Empirical results verify the accuracy of performance prediction across model sizes based on information capacity and show the correlation between information capacity and benchmark scores.
Open paper
IDALC: A Semi-Supervised Framework for Intent Detection and Active Learning based Correction

Ankan Mullick, Sukannya Purkayastha, Saransh Sharma, Pawan Goyal, Niloy Ganguly · Nov 8, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • In this paper, we introduce IDALC (Intent Detection and Active Learning based Correction), a semi-supervised framework designed to detect user intents and rectify system-rejected utterances while minimizing the need for human annotation.
  • Empirical findings on various benchmark datasets demonstrate that our system surpasses baseline methods, achieving a 5-10% higher accuracy and a 4-8% improvement in macro-F1.
Open paper
Batch Prompting Suppresses Overthinking Reasoning Under Constraint: How Batch Prompting Suppresses Overthinking in Reasoning Models

Saurabh Srivastava, Janit Bidhan, Hao Yan, Abhishek Dey, Tanu Kansal, Paras Kath · Nov 6, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics General
  • Across 13 diverse benchmarks with DeepSeek-R1 and OpenAI-o1, batch prompting {reduces reasoning tokens by 76\% (2{,}950\mapsto710), on average, while preserving or improving accuracy}.
Open paper
STARS: Synchronous Token Alignment for Robust Supervision in Large Language Models

Mohammad Atif Quamar, Mohammad Areeb, Mikhail Kuznetsov, Muslum Ozgur Ozmen, Z. Berkay Celik · Nov 5, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics Coding
  • Aligning large language models (LLMs) with human values is crucial for safe deployment.
  • On the HH-RLHF benchmark, we demonstrate that STARS achieves competitive alignment quality with that of state-of-the-art dynamic methods, while strictly bounding rejection costs and maximizing system throughput.
Open paper
Mina: A Multilingual LLM-Powered Legal Assistant Agent for Bangladesh for Empowering Access to Justice

Azmine Toushik Wasi, Wahid Faisal, Mst Rafia Islam, Md Rizwan Parvez · Nov 4, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics LawMultilingual
  • Evaluated by law faculty from leading Bangladeshi universities across all stages of the 2022 and 2023 Bangladesh Bar Council Exams, Mina scored 75-80% in Preliminary MCQs, Written, and simulated Viva Voce exams, matching or surpassing…
  • Even under a conservative upper bound, Mina operates at just 0.12-0.61% of typical legal consultation costs in Bangladesh, yielding a 99.4-99.9\% cost reduction relative to human-provided services.
Open paper
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains

Tian Liang, Wenxiang Jiao, Zhiwei He, Jiahao Xu, Haitao Mi, Dong Yu · Oct 31, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics Math
  • Experimental results on challenging mathematical benchmarks show that DeepCompress consistently outperforms baseline methods, achieving superior accuracy while significantly improving token efficiency.
Open paper
Human or LLM as Standardized Patients? A Comparative Study for Medical Education

Bingquan Zhang, Xiaoxiao Liu, Yuchi Wang, Lei Zhou, Qianqian Xie, Benyou Wang · Nov 12, 2025

Citations: 0

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

Score: 78% Moderate protocol signal Freshness: Cold Status: Fallback
Automatic Metrics Multi Agent Medicine
  • Although large language model (LLM)-based virtual standardized patients (VSPs) have been proposed as an alternative, their behavior remains unstable and lacks rigorous comparison with human standardized patients.
  • We propose EasyMED, a multi-agent VSP framework that separates case-grounded information disclosure from response generation to support stable, inquiry-conditioned patient behavior.
Open paper

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

Score: 78% Moderate protocol signal Freshness: Cold Status: Fallback
Simulation Env Multi Agent General
  • The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device…
  • Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with…
Open paper
LexInstructEval: Lexical Instruction Following Evaluation for Large Language Models

Huimin Ren, Yan Liang, Baiqiao Su, Chaobo Sun, Hengtong Lu, Kaike Zhang · Nov 13, 2025

Citations: 0

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

Score: 75% Moderate protocol signal Freshness: Cold Status: Fallback
Human EvalLlm As Judge General
  • Current methods either rely on subjective and costly human evaluation or on automated LLM-as-a-judge systems, which suffer from inherent biases and unreliability.
  • To address these limitations, we introduce LexInstructEval, a new benchmark and evaluation framework for fine-grained lexical instruction following.
Open paper
OckBench: Measuring the Efficiency of LLM Reasoning

Zheng Du, Hao Kang, Song Han, Tushar Krishna, Ligeng Zhu · Nov 7, 2025

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 33% Moderate protocol signal Freshness: Cold Status: Ready
Automatic Metrics Coding
  • Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage.
  • Thus, we introduce OckBench, the first benchmark that jointly measures accuracy and token efficiency across reasoning and coding tasks.
Open paper
Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation

Lingyue Fu, Bolun Zhang, Hao Guan, Yaoming Zhu, Lin Qiu, Weiwen Liu · Oct 28, 2025

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 33% Moderate protocol signal Freshness: Cold Status: Ready
Expert Verification Llm As JudgeAutomatic Metrics Coding
  • To address these challenges, we propose an agent-driven benchmark construction pipeline that leverages human supervision to efficiently generate diverse project-level tasks.
  • Furthermore, to overcome the inaccuracy of general LLM judges, we propose a highly reliable evaluation framework powered by a specialized, fine-tuned model.
Open paper
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces

Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury · Nov 10, 2025

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 33% High protocol signal Freshness: Cold Status: Fallback
Automatic Metrics Long Horizon Coding
  • On the Episodic Memory Benchmark (EpBench) huet_episodic_2025 comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to 20\%.
  • More broadly, GSW offers a concrete blueprint for endowing LLMs with human-like episodic memory, paving the way for more capable agents that can reason over long horizons.
Open paper

Protocol Hubs

Benchmark 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.