Image de couverture de livre

SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Jiamin, Wu, Yidi, Wang, Qiexiang, Chen, Qianben, Li, Yuchen, Zhang, Yansen, Zhang, Xiaokun, Zhou, Wangchunshu, Ma, Chen
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation
par: Chen, Jiamin, et autres
Publié: (2025)

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
par: Wang, Piaohong, et autres
Publié: (2025)

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
par: Yao, Yi, et autres
Publié: (2026)

MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark
par: Chen, Dongping, et autres
Publié: (2024)

Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
par: Chen, Junjie, et autres
Publié: (2026)

AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
par: Zhang, Guibin, et autres
Publié: (2025)

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
par: Chen, Qianben, et autres
Publié: (2026)

FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge
par: Yang, Bo, et autres
Publié: (2026)

PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
par: Tao, Meiling, et autres
Publié: (2025)

SEAL: Steerable Reasoning Calibration of Large Language Models for Free
par: Chen, Runjin, et autres
Publié: (2025)

Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
par: Qin, Tianrui, et autres
Publié: (2025)

JudgeSense: A Benchmark for Prompt Sensitivity in LLM-as-a-Judge Systems
par: Bellibatlu, Rohith Reddy, et autres
Publié: (2026)

HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
par: Yang, Langqi, et autres
Publié: (2025)

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
par: Shen, Han, et autres
Publié: (2024)

SEAL: Synergistic Co-Evolution of Agents and Learning Environments
par: Hu, Yihao, et autres
Publié: (2026)

Symbolic Learning Enables Self-Evolving Agents
par: Zhou, Wangchunshu, et autres
Publié: (2024)

CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?
par: Zhao, Yuwei, et autres
Publié: (2024)

Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
par: Zhang, Qiyuan, et autres
Publié: (2025)

TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
par: Wang, Yidong, et autres
Publié: (2025)

CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks
par: Jiang, Hongchao, et autres
Publié: (2025)

Teach2Eval: An Indirect Evaluation Method for LLM by Judging How It Teaches
par: Zhou, Yuhang, et autres
Publié: (2025)

TaskCraft: Automated Generation of Agentic Tasks
par: Shi, Dingfeng, et autres
Publié: (2025)

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
par: Chen, Qianben, et autres
Publié: (2025)

Less Is More: Elevating RAG via Performance-Driven Context Compression
par: Cui, Ziqiang, et autres
Publié: (2025)

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
par: Yuan, Tongxin, et autres
Publié: (2024)

Can LLMs be Good Graph Judge for Knowledge Graph Construction?
par: Huang, Haoyu, et autres
Publié: (2024)

Can LLM be a Personalized Judge?
par: Dong, Yijiang River, et autres
Publié: (2024)

Benchmarks Saturate When The Model Gets Smarter Than The Judge
par: Ballon, Marthe, et autres
Publié: (2026)

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
par: Wang, Leyao, et autres
Publié: (2026)

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References
par: Zhang, Qiyuan, et autres
Publié: (2024)

Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
par: Zhou, Yilun, et autres
Publié: (2025)

DTVLT: A Multi-modal Diverse Text Benchmark for Visual Language Tracking Based on LLM
par: Li, Xuchen, et autres
Publié: (2024)

RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator
par: Tang, Zhenwei, et autres
Publié: (2026)

How Far Are We from Genuinely Useful Deep Research Agents?
par: Zhang, Dingling, et autres
Publié: (2025)

MM-Eval: A Multilingual Meta-Evaluation Benchmark for LLM-as-a-Judge and Reward Models
par: Son, Guijin, et autres
Publié: (2024)

Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
par: He, Bowei, et autres
Publié: (2025)

CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation
par: Zhu, Ziyi, et autres
Publié: (2026)

Evaluating Scoring Bias in LLM-as-a-Judge
par: Li, Qingquan, et autres
Publié: (2025)

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
par: Tong, Terry, et autres
Publié: (2025)

SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
par: Zhang, Yansen, et autres
Publié: (2025)