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: 474 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.

KLong: Training LLM Agent for Extremely Long-horizon Tasks

Yue Liu, Yingwei Ma, Yibo Miao, Yanhao Li, Yuchong Xie, Xinlong Yang · Feb 19, 2026

Citations: 0

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

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Rubric Rating Long Horizon Coding
  • Then, we introduce Research-Factory, an automated pipeline that generates high-quality training data by collecting research papers and constructing evaluation rubrics.
  • Notably, our proposed KLong (106B) surpasses Kimi K2 Thinking (1T) by 11.28% on PaperBench, and the performance improvement generalizes to other coding benchmarks like SWE-bench Verified and MLE-bench.
Open paper
Discrete Stochastic Localization for Non-autoregressive Generation

Yunshu Wu, Jiayi Cheng, Partha Thakuria, Rob Brekelmans, Evangelos E. Papalexakis, Greg Ver Steeg · Feb 18, 2026

Citations: 0

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

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • On OpenWebText, DSL fine-tuning yields large MAUVE gains at low step budgets, surpassing the MDLM+ReMDM baseline with \(\sim\)4\times fewer denoiser evaluations, and matches autoregressive quality at high budgets.
Open paper
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

Lingxiang Hu, Yiding Sun, Tianle Xia, Wenwei Li, Ming Xu, Liqun Liu · Feb 15, 2026

Citations: 0

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

Score: 83% High protocol signal Freshness: Warm Status: Ready
Expert Verification Simulation Env Long Horizon Coding
  • While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem.
  • To address this gap, we propose AD-Bench, a benchmark designed based on real-world business requirements of advertising and marketing platforms.
Open paper
ALPS: A Diagnostic Challenge Set for Arabic Linguistic & Pragmatic Reasoning

Hussein S. Al-Olimat, Ahmad Alshareef · Feb 19, 2026

Citations: 0

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

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Multilingual
  • We introduce ALPS (Arabic Linguistic & Pragmatic Suite), a native, expert-curated diagnostic challenge set probing Deep Semantics and Pragmatics, capabilities that complement specialized large-scale benchmarks.
  • While top commercial models (Gemini-3-flash at 94.2%) surpass the average single human, a substantial gap persists between commercial giants and Arabic-native models, with the best Arabic-specific model (Jais-2-70B at 83.6%) approaching but…
Open paper
Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect

Minh Duc Bui, Manuel Mager, Peter Herbert Kann, Katharina von der Wense · Feb 18, 2026

Citations: 0

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

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • We introduce a digital dictionary-an NLP-ready dataset derived from an existing resource (Schramm, 1966)-to support researchers in modeling and benchmarking the language.
Open paper
Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents

Wenxuan Ding, Nicholas Tomlin, Greg Durrett · Feb 18, 2026

Citations: 0

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

Score: 77% Sparse protocol signal Freshness: Warm Status: Ready
Coding
  • Each problem has latent environment state that can be reasoned about via a prior which is passed to the LLM agent.
  • Our results on information-seeking QA and on a simplified coding task show that making cost-benefit tradeoffs explicit with CTA can help agents discover more optimal decision-making strategies.
Open paper
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents

Zheng Chu, Xiao Wang, Jack Hong, Huiming Fan, Yuqi Huang, Yue Yang · Feb 15, 2026

Citations: 0

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

Score: 83% Moderate protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Tool Use Coding
  • To address these challenges, we propose REDSearcher, a unified framework that codesigns complex task synthesis, midtraining, and posttraining for scalable searchagent optimization.
  • Across both textonly and multimodal searchagent benchmarks, our approach achieves stateoftheart performance.
Open paper
Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution

Nithin Sivakumaran, Shoubin Yu, Hyunji Lee, Yue Zhang, Ali Payani, Mohit Bansal · Feb 18, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 38% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • On multiple reasoning benchmarks (BIG-Bench Extra Hard, MuSR, ZebraLogicBench, and FOLIO), REMUL consistently and substantially improves three measures of faithfulness -- hint attribution, early answering area over the curve (AOC), and…
Open paper
MAGE: All-[MASK] Block Already Knows Where to Look in Diffusion LLM

Omin Kwon, Yeonjae Kim, Doyeon Kim, Minseo Kim, Yeonhong Park, Jae W. Lee · Feb 15, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 38% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • Across long-context benchmarks including LongBench and Needle-in-a-Haystack, MAGE achieves near-lossless accuracy with a fraction of the KV budget while delivering up to 3-4x end-to-end speedup, consistently outperforming AR-oriented sparse…
Open paper
What Language is This? Ask Your Tokenizer

Clara Meister, Ahmetcan Yavuz, Pietro Lesci, Tiago Pimentel · Feb 19, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 35% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Multilingual
  • Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training data analysis, and cross-lingual evaluation of large language models.
  • Empirical evaluations against widely used baselines, including fastText, GlotLID, and CLD3, show that UniLID achieves competitive performance on standard benchmarks, substantially improves sample efficiency in low-resource settings -…
Open paper
Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 35% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Medicine
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
Emotion Collider: Dual Hyperbolic Mirror Manifolds for Sentiment Recovery via Anti Emotion Reflection

Rong Fu, Ziming Wang, Shuo Yin, Haiyun Wei, Kun Liu, Xianda Li · Feb 18, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 35% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • Emotional expression underpins natural communication and effective human-computer interaction.
  • Empirical results on standard multimodal emotion benchmarks show that EC-Net produces robust, semantically coherent representations and consistently improves accuracy, particularly when modalities are partially available or contaminated by…
Open paper
GPT-5 vs Other LLMs in Long Short-Context Performance

Nima Esmi, Maryam Nezhad-Moghaddam, Fatemeh Borhani, Asadollah Shahbahrami, Amin Daemdoost, Georgi Gaydadjiev · Feb 15, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 35% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Math
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
GLM-5: from Vibe Coding to Agentic Engineering

GLM-5-Team, :, Aohan Zeng, Xin Lv, Zhenyu Hou, Zhengxiao Du · Feb 17, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 32% Sparse protocol signal Freshness: Warm Status: Ready
Long Horizon Coding
  • We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering.
  • Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively.
Open paper
Selective Synchronization Attention

Hasi Hays · Feb 16, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 32% Sparse protocol signal Freshness: Warm Status: Ready
General
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos

Laura De Grazia, Danae Sánchez Villegas, Desmond Elliott, Mireia Farrús, Mariona Taulé · Feb 17, 2026

Citations: 0

Match reason: Matched by broad semantic/index fallback.

Score: 28% Sparse protocol signal Freshness: Warm Status: Ready
General
  • Our findings indicate that multimodal LLMs perform competitively with human annotators in identifying nuanced forms of sexism; however, they struggle to capture co-occurring sexist types when these are conveyed through visual cues.
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.