Look Before you Leap: Estimating LLM Benchmark Scores from Descriptions

• URL: http://arxiv.org/abs/2509.20645v1
• Date: Thu, 25 Sep 2025 01:02:27 GMT
• Title: Look Before you Leap: Estimating LLM Benchmark Scores from Descriptions
• Authors: Jungsoo Park, Ethan Mendes, Gabriel Stanovsky, Alan Ritter,
• Abstract summary: We study text-only performance forecasting, estimating a model's score from a redacted task description and intended configuration.<n>To support systematic study, we curate PRECOG, a corpus of redacted description-performance pairs spanning diverse tasks, domains, and metrics.<n>Experiments show the task is challenging but feasible, reaching mean absolute error as low as 8.7 on the Accuracy subset at high-confidence thresholds.
• Score: 35.48753431700434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Progress in large language models is constrained by an evaluation bottleneck: build a benchmark, evaluate models and settings, then iterate. We therefore ask a simple question: can we forecast outcomes before running any experiments? We study text-only performance forecasting: estimating a model's score from a redacted task description and intended configuration, with no access to dataset instances. To support systematic study, we curate PRECOG, a corpus of redacted description-performance pairs spanning diverse tasks, domains, and metrics. Experiments show the task is challenging but feasible: models equipped with a retrieval module that excludes source papers achieve moderate prediction performance with well-calibrated uncertainty, reaching mean absolute error as low as 8.7 on the Accuracy subset at high-confidence thresholds. Our analysis indicates that stronger reasoning models engage in diverse, iterative querying, whereas current open-source models lag and often skip retrieval or gather evidence with limited diversity. We further test a zero-leakage setting, forecasting on newly released datasets or experiments before their papers are indexed, where GPT-5 with built-in web search still attains nontrivial prediction accuracy. Overall, our corpus and analyses offer an initial step toward open-ended anticipatory evaluation, supporting difficulty estimation and smarter experiment prioritization.

Related papers

• Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting [18.018179328110048]
  We introduce a predictability-aligned diagnostic framework grounded in spectral coherence.<n>We provide the first systematic evidence of "predictability drift", demonstrating that a task's forecasting difficulty varies sharply over time.<n>Our evaluation reveals a key architectural trade-off: complex models are superior for low-predictability data, whereas linear models are highly effective on more predictable tasks.
  arXiv  Detail & Related papers  (2025-09-27T02:56:06Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.<n>We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.<n>We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Precise Model Benchmarking with Only a Few Observations [6.092112060364272]
  We propose an empirical Bayes (EB) estimator that balances direct and regression estimates for each subgroup separately. EB consistently provides more precise estimates of the LLM performance compared to the direct and regression approaches.
  arXiv  Detail & Related papers  (2024-10-07T17:26:31Z)
• Investigating the Impact of Hard Samples on Accuracy Reveals In-class Data Imbalance [4.291589126905706]
  In the AutoML domain, test accuracy is heralded as the quintessential metric for evaluating model efficacy. However, the reliability of test accuracy as the primary performance metric has been called into question. The distribution of hard samples between training and test sets affects the difficulty levels of those sets. We propose a benchmarking procedure for comparing hard sample identification methods.
  arXiv  Detail & Related papers  (2024-09-22T11:38:14Z)
• Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection [10.301985230669684]
  This paper presents a comprehensive analysis of GPT-4, GPT-3.5 Turbo, and FLAN-T5 models in detecting framing in news headlines. We evaluated these models in various scenarios: zero-shot, few-shot with in-domain examples, cross-domain examples, and settings where models explain their predictions.
  arXiv  Detail & Related papers  (2024-02-18T15:27:48Z)
• A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis [90.24921443175514]
  We focus on aspect-based sentiment analysis, which involves extracting aspect term, category, and predicting their corresponding polarities. We propose to reformulate the extraction and prediction tasks into the sequence generation task, using a generative language model with unidirectional attention. Our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.
  arXiv  Detail & Related papers  (2022-04-11T18:31:53Z)
• Boost Test-Time Performance with Closed-Loop Inference [85.43516360332646]
  We propose to predict hard-classified test samples in a looped manner to boost the model performance. We first devise a filtering criterion to identify those hard-classified test samples that need additional inference loops. For each hard sample, we construct an additional auxiliary learning task based on its original top-$K$ predictions to calibrate the model.
  arXiv  Detail & Related papers  (2022-03-21T10:20:21Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)
• Evaluating Models' Local Decision Boundaries via Contrast Sets [119.38387782979474]
  We propose a new annotation paradigm for NLP that helps to close systematic gaps in the test data. We demonstrate the efficacy of contrast sets by creating them for 10 diverse NLP datasets. Although our contrast sets are not explicitly adversarial, model performance is significantly lower on them than on the original test sets.
  arXiv  Detail & Related papers  (2020-04-06T14:47:18Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.