Improved LLM as a Judge Techniques

haritha13131 pts0 comments

[2606.27226] Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

-->

Computer Science > Artificial Intelligence

arXiv:2606.27226 (cs)

[Submitted on 25 Jun 2026]

Title:Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

Authors:Sangwoo Cho, Kushal Chawla, Pengshan Cai, Zefang Liu, Chenyang Zhu, Shi-Xiong Zhang, Sambit Sahu<br>View a PDF of the paper titled Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement, by Sangwoo Cho and 6 other authors

View PDF<br>HTML (experimental)

Abstract:Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores. Given a task prompt, a meta-prompt generates fine-grained evaluation questions, and an LLM answers them independently for each output, yielding transparent question-level feedback together with calibrated overall scores. This decomposition makes evaluation easier to inspect, easier to diagnose, and directly usable for prompt improvement. Across SummEval, Topical-Chat, and QAGS, BINEVAL matches or outperforms strong baselines including UniEval and G-Eval, with especially strong results on factual consistency benchmarks such as QAGS. Beyond competitive correlation with human judgments, BINEVAL better matches human score distributions and avoids the ceiling effects common in prior LLM judges, leading to better discrimination between borderline and clearly flawed outputs. We further show that the same question-level feedback supports iterative prompt optimization, improving evaluator prompts on summarization and generation prompts on IFBench under both self-update and cross-model update settings. Overall, BINEVAL provides a task-agnostic, training-free, and interpretable evaluation framework that combines strong empirical performance with practical diagnostic and optimization value.

Comments:<br>Acceepted to the Second Workshop on Compositional Learning at ICML 2026, Seoul, South Korea

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as:<br>arXiv:2606.27226 [cs.AI]

(or<br>arXiv:2606.27226v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2606.27226

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Sangwoo Cho [view email]<br>[v1]<br>Thu, 25 Jun 2026 16:14:50 UTC (603 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement, by Sangwoo Cho and 6 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2026-06

Change to browse by:

cs<br>cs.CL

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

toggle evaluation arxiv questions interpretable view

Related Articles