# EvalAgent: Discovering Implicit Evaluation Criteria from the Web

arXiv: https://arxiv.org/abs/2504.15219 · HTML: https://mlsanity.com/paper/2504.15219/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 24 of 24)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Self-Rewarding Language Models](https://mlsanity.com/paper/2401.10020/) (2024)
- [Generative Verifiers: Reward Modeling as Next-Token Prediction](https://mlsanity.com/paper/2408.15240/) (2024)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [Is Self-Repair a Silver Bullet for Code Generation?](https://mlsanity.com/paper/2306.09896/) (2023)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Complex Claim Verification with Evidence Retrieved in the Wild](https://mlsanity.com/paper/2305.11859/) (2023)
- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models](https://mlsanity.com/paper/2406.05761/) (2024)
- [Are Large Language Models Capable of Generating Human-Level Narratives?](https://mlsanity.com/paper/2407.13248/) (2024)
- [COLLIE: Systematic Construction of Constrained Text Generation Tasks](https://mlsanity.com/paper/2307.08689/) (2023)
- [TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation](https://mlsanity.com/paper/2410.03608/) (2024)
- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)
- [Learning to Refine with Fine-Grained Natural Language Feedback](https://mlsanity.com/paper/2407.02397/) (2024)
- [VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models](https://mlsanity.com/paper/2410.12851/) (2024)
- [Using Natural Language Explanations to Rescale Human Judgments](https://mlsanity.com/paper/2305.14770/) (2023)
- [DOLOMITES: Domain-Specific Long-Form Methodical Tasks](https://mlsanity.com/paper/2405.05938/) (2024)

## Built on by (most cited first, 11 of 11)

- [ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics](https://mlsanity.com/paper/2509.00496/) (2025)
- [Self-Improvements in Modern Agentic Systems: A Survey](https://mlsanity.com/paper/2607.13104/) (2026)
- [Agent-as-a-Judge](https://mlsanity.com/paper/2601.05111/) (2026)
- [Qworld: Question-Specific Evaluation Criteria for LLMs](https://mlsanity.com/paper/2603.23522/) (2026)
- [CREATE: Testing LLMs for Associative Creativity](https://mlsanity.com/paper/2603.09970/) (2026)
- [From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape](https://mlsanity.com/paper/2606.08625/) (2026)
- [DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents](https://mlsanity.com/paper/2606.17029/) (2026)
- [Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification](https://mlsanity.com/paper/2607.25904/) (2026)
- [BehaviorSFT: Behavioral Token Conditioning for Clinical Agents Across the Proactivity Spectrum](https://mlsanity.com/paper/2505.21757/) (2025)
- [From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs](https://mlsanity.com/paper/2604.14137/) (2026)
- [FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents](https://mlsanity.com/paper/2609.35744/) (2026)

## Abstract (arXiv)

Evaluation of language model outputs on structured writing tasks is typically conducted with a number of desirable criteria presented to human evaluators or large language models (LLMs). For instance, on a prompt like "Help me draft an academic talk on coffee intake vs research productivity", a model response may be evaluated for criteria like accuracy and coherence. However, high-quality responses should do more than just satisfy basic task requirements. An effective response to this query should include quintessential features of an academic talk, such as a compelling opening, clear research questions, and a takeaway. To help identify these implicit criteria, we introduce EvalAgent, a novel framework designed to automatically uncover nuanced and task-specific criteria. EvalAgent first mines expert-authored online guidance. It then uses this evidence to propose diverse, long-tail evaluation criteria that are grounded in reliable external sources. Our experiments demonstrate that the grounded criteria produced by EvalAgent are often implicit (not directly stated in the user's prompt), yet specific (high degree of lexical precision). Further, EvalAgent criteria are often not satisfied by initial responses but they are actionable, such that responses can be refined to satisfy them. Finally, we show that combining LLM-generated and EvalAgent criteria uncovers more human-valued criteria than using LLMs alone.