REVIEW 10 cited by
Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Adaptive Testing for LLM Evaluation: A Psychometric Alternative to Static Benchmarks
read the original abstract
Evaluating large language models (LLMs) typically requires thousands of benchmark items, making the process expensive, slow, and increasingly impractical at scale. Existing evaluation protocols rely on average accuracy over fixed item sets, treating all items as equally informative despite substantial variation in difficulty and discrimination. We introduce ATLAS, an adaptive testing framework based on Item Response Theory (IRT) that estimates model ability using Fisher information-guided item selection. ATLAS reduces the number of required items by up to 90% while maintaining measurement precision. For instance, it matches whole-bank ability estimates using only 41 items (0.157 MAE) on HellaSwag (5,600 items). We further reconstruct accuracy from ATLAS's ability estimates and find that reconstructed accuracies closely match raw accuracies across all five benchmarks, indicating that ability ${\theta}$ preserves the global performance structure. At the same time, ${\theta}$ provides finer discrimination within accuracy-equivalent models: among more than 3,000 evaluated models, 23-31% shift by more than 10 rank positions, and models with identical accuracies receive meaningfully different ability estimates. Code and calibrated item banks are available at https://github.com/Peiyu-Georgia-Li/ATLAS.git.
Forward citations
Cited by 10 Pith papers
-
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Introduces the first community-governed unified JSON schema and crowdsourced repository for AI evaluation results, with converters and a database spanning 22,235 models and 2,273 benchmarks.
-
The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs
Using a 1PL IRT model on real cultural questions across 13 locales, the study identifies a local-language knowledge-access advantage masked by lower proficiency in raw accuracy.
-
FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses
FailureScope clusters evaluation probes by cross-model failure patterns via LOMO to produce stable taxonomies that generalize across single-turn, multi-turn, and adversarial regimes, with reported metrics of Kendall's...
-
Auditing LLM Benchmarks with Item Response Theory
An IRT-based detector identifies mislabeled examples in LLM benchmarks at 95% precision in the top 200 cases, outperforming supervised classifiers and revealing reward-model specialization on style over facts.
-
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
ECC calibrates semantic embeddings with posterior model comparisons and Bradley-Terry capability profiles to create flexible, mixed-membership query clusters that improve LLM capability ranking.
-
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
ECC calibrates semantic embeddings with model comparisons via Bradley-Terry profiles and mixture weights to cluster queries by latent LLM capabilities, claiming 17-18 point gains in ranking quality over baselines.
-
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
Dynamic Boundary Evaluation locates each LLM's performance boundary at ~50% pass probability via a calibrated item bank and Skill-Guided Boundary Search algorithm to enable unified, adaptive evaluations across safety,...
-
Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models
Dynamic Boundary Evaluation adaptively identifies each LLM's performance boundary on a shared difficulty scale using a calibrated item bank and a search algorithm.
-
Growing Pains: Extensible and Efficient LLM Benchmarking Via Fixed Parameter Calibration
A fixed-parameter multidimensional IRT calibration approach allows extending LLM benchmark suites over time, predicting full performance within 2-3 points and preserving rankings (Spearman ρ ≥ 0.9) using only 100 anch...
-
DualEval: Joint Model-Item Calibration for Unified LLM Evaluation
DualEval jointly calibrates LLM abilities and item difficulties/sharpness in a shared latent space using static labels and reward-model scores to unify benchmark and arena-style evaluation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.