MétaCan
Menu
← Back to cohort
Record W7082255410 · doi:10.48448/v1pp-6e61

ChatBench: From Static Benchmarks to Human-AI Evaluation

2025· other· en· W7082255410 on OpenAlexaff

Bibliographic record

VenueUnderline Science Inc. · 2025
Typeother
Languageen
FieldComputer Science
TopicGeochemistry and Geologic Mapping
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsMeasure (data warehouse)ConversationIsolation (microbiology)Scale (ratio)Carry (investment)Key (lock)

Abstract

fetched live from OpenAlex

With the rapid adoption of LLM-based chat-bots, there is a pressing need to evaluate what humans and LLMs can achieve together. However, standard benchmarks, such as MMLU, measure LLM capabilities in isolation (i.e., “AI-alone”). Here, we design and conduct a user study to convert MMLU questions into user-AI conversations, by seeding the user with the question and having them carry out a conversation with the LLM to answer their question. We release ChatBench, a new dataset with AI-alone, user-alone, and user-AI data for 396 questions and two LLMs, including 144K answers and 7,336 user-AI conversations. We find that AI-alone accuracy fails to predict user-AI accuracy, with significant differences across multiple subjects (math, physics, and moral reasoning), and we analyze the user-AI conversations to provide insight into how they diverge from AI-alone benchmarks. Finally, we show that fine-tuning a user simulator on a subset of ChatBench improves its ability to estimate user-AI accuracies, increasing correlation on held-out questions by more than 20 points, creating possibilities for scaling interactive evaluation.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.016
metaresearch head score (Gemma)0.087
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.016
Threshold uncertainty score0.084

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0160.087
Meta-epidemiology (narrow)0.0040.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0070.004
Science and technology studies0.0020.002
Scholarly communication0.0040.006
Open science0.0040.006
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0050.008

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.025
GPT teacher head0.321
Teacher spread0.296 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueUnderline Science Inc.→Same topicGeochemistry and Geologic Mapping→French-language works237,207→