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: 268 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.

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • Crucially, the photonic advantage grows with context length: as N increases, the electronic scan cost rises linearly while the photonic evaluation remains O(1).
  • Hardware-impaired needle-in-a-haystack evaluation on Qwen2.5-7B confirms 100% accuracy from 4K through 64K tokens at k=32, with 16x traffic reduction at 64K context.
Open paper
DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment

James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith · Mar 23, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% High protocol signal Freshness: Warm Status: Ready
Pairwise Preference Automatic Metrics General
  • Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility.
  • We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional.
Open paper
What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?

Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard, Wei Zhao · Mar 19, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics CodingMultilingual
  • We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, German, Chinese, Arabic, and Hausa) and…
  • We evaluate 20 LLMs and introduce the multilingual Date Fragmentation Ratio (mDFR), calibrated with human severity ratings, together with geometric-probing analyses of internal temporal representations.
Open paper
Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval

Hangeol Chang, Changsun Lee, Seungjoon Rho, Junho Yeo, Jong Chul Ye · Mar 19, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
Memento-Skills: Let Agents Design Agents

Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, Ziqin Gong, Bowen Zhao · Mar 19, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • We introduce Memento-Skills, a generalist, continually-learnable LLM agent system that functions as an agent-designing agent: it autonomously constructs, adapts, and improves task-specific agents through experience.
  • Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2\% and 116.2\% relative improvements in overall accuracy, respectively.
Open paper

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • We construct a large-scale training dataset of 234,770 CVE descriptions with AI-refined CWE labels using Claude Sonnet 4.6, and agreement-filtered evaluation sets where NVD and AI labels agree.
  • On the external CTI-Bench benchmark (NeurIPS 2024), the model achieves 75.6% strict accuracy (95% CI: 72.8-78.2%) -- statistically indistinguishable from Cisco Foundation-Sec-8B-Reasoning (75.3%, 8B parameters) at 64x fewer parameters.
Open paper
Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan, Xueyi Pu · Mar 16, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% High protocol signal Freshness: Warm Status: Ready
Pairwise Preference Automatic Metrics Coding
  • To address these challenges, we introduce SDiaReward, an end-to-end multi-turn reward model trained on SDiaReward-Dataset, a novel collection of episode-level preference pairs explicitly targeting these gaps.
  • Experiments demonstrate that SDiaReward achieves state-of-the-art pairwise preference accuracy, significantly outperforming general-purpose audio LLMs.
Open paper
CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

Junhang Cheng, Fang Liu, Jia Li, Chengru Wu, Nanxiang Jiang, Li Zhang · Mar 15, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics CodingMultilingual
  • To address this gap, we introduce CangjieBench, a contamination-free benchmark for Cangjie, a representative low-resource general-purpose language.
  • Agent achieve state-of-the-art accuracy but incur high token consumption.
Open paper

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Llm As JudgeAutomatic Metrics Long Horizon General
  • Across four LLM backbones, DCS consistently outperforms supervised probes and LLM-as-judge baselines, achieving up to 71.1% accuracy on sentence-level hawkish--dovish classification.
Open paper
FGTR: Fine-Grained Multi-Table Retrieval via Hierarchical LLM Reasoning

Chaojie Sun, Bin Cao, Tiantian Li, Chenyu Hou, Ruizhe Li, Jing Fan · Mar 13, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • To this end, we propose a hierarchical multi-table query method based on LLM: Fine-Grained Multi-Table Retrieval FGTR, a new retrieval paradigm that employs a human-like reasoning strategy.
  • To comprehensively evaluate the performance of FGTR, we construct two new benchmark datasets based on Spider and BIRD .
Open paper

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • Extensive experiments on both in-domain and out-of-domain benchmarks validate the superiority and effectiveness of DDPO.
  • Compared to GRPO, DDPO reduces the average answer length by 12% while improving accuracy by 1.85% across multiple benchmarks, achieving a better trade-off between accuracy and length.
Open paper
EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models

Minsoo Cheong, Donghyun Son, Woosang Lim, Sungjoo Yoo · Mar 19, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • Experiments on LLaDA-8B-Instruct and Dream-7B-Instruct show that EntropyCache achieves 15.2\times-26.4\times speedup on standard benchmarks and 22.4\times-24.1\times on chain-of-thought benchmarks, with competitive accuracy and decision…
Open paper
Probing Cultural Signals in Large Language Models through Author Profiling

Valentin Lafargue, Ariel Guerra-Adames, Emmanuelle Claeys, Elouan Vuichard, Jean-Michel Loubes · Mar 17, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
Open paper
PCodeTrans: Translate Decompiled Pseudocode to Compilable and Executable Equivalent

Yuxin Cui, Zeyu Gao, Shuxian He, Siliang Qin, Chao Zhang · Mar 16, 2026

Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 80% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics Coding
  • Decompilation is foundational to binary analysis, yet conventional tools prioritize human readability over strict recompilability and verifiable runtime correctness.
  • While recent LLM-based approaches attempt to refine decompiled pseudocode, they typically either optimize solely for readability or rely on static analysis for evaluation.
Open paper
Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon Coding
  • Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous…
  • In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0).
Open paper

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Multi Agent LawCoding
  • LLM coding benchmarks face a credibility crisis: widespread solution leakage and test quality issues undermine SWE-bench Verified, while existing detection methods--paraphrase consistency, n-gram overlap, perplexity analysis--never directly…
  • We introduce Cross-Context Verification (CCV), a black-box method that solves the same benchmark problem in N independent sessions and measures solution diversity, combined with the Hierarchical Cross-Context Architecture (HCCA), a…
Open paper
Citations: 0

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% Moderate protocol signal Freshness: Warm Status: Fallback
Llm As JudgeAutomatic Metrics Coding
  • We evaluate LLM-as-a-judge marking across three physics assessment formats - structured questions, written essays, and scientific plots - comparing GPT-5.2, Grok 4.1, Claude Opus 4.5, DeepSeek-V3.2, Gemini Pro 3, and committee aggregations…
  • Across n=55 scripts (n=275 essays), blind AI marking is harsher and more variable than human marking, with discriminative validity already poor (ρ\approx 0.1).
Open paper

Match reason: Keyword overlap 2/2 across title and protocol fields.

Score: 83% High protocol signal Freshness: Warm Status: Fallback
Automatic Metrics Long Horizon Math
  • Empirical validation on GPQA and GSM8K benchmarks indicates that Top-b significantly reduces generation entropy and inter-decoding variance while maintaining competitive reasoning accuracy, effectively approximating a self-regulating…
Open paper

Match reason: Keyword overlap 1/2 across title and protocol fields.

Score: 57% Moderate protocol signal Freshness: Warm Status: Ready
Automatic Metrics General
  • As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime.
  • We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models.
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.