What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation

• URL: http://arxiv.org/abs/2608.22948v1
• Date: Mon, 24 Aug 2026 08:17:01 GMT
• Title: What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation
• Abstract summary: We introduce a benchmark that carries a proposal from Literature to Test: the Lit2Test benchmark centers on a six-field contract organized around a falsifying outcome.<n>Built prospectively from 200 real-paper neighborhoods, Lit2Test elicits proposals from four frontier models and compares them through 1,200 pairwise comparisons judged blind in both presentation orders.<n>The protocol audits its own reliability through diagnostic controls and bounded human calibration, with three annotators corroborating the conclusions within explicitly stated reliability bounds.
• Score: 23.50765366373648
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are increasingly used to propose research ideas, yet the prevailing ways of judging such ideas supply no shared decision rule: free-form judging sways with style and position, and scoring against a later paper rewards recovery of one realized trajectory. We introduce a benchmark that carries a proposal from Literature to Test: the Lit2Test benchmark centers on a six-field contract organized around a falsifying outcome, so that every proposal precommits the observation that would prove it wrong, making its quality decidable in the first place rather than merely arguable. Built prospectively from 200 real-paper neighborhoods, Lit2Test elicits proposals from four frontier models and compares them through 1,200 pairwise comparisons judged blind in both presentation orders. The protocol audits its own reliability through diagnostic controls and bounded human calibration, with three annotators corroborating the conclusions within explicitly stated reliability bounds. Lit2Test recovers a strict ranking of the four models in all 10,000 bootstrap replicates, and the separation comes from the quality of the proposed tests and metrics rather than from surface fluency. We release the benchmark, construction pipeline, and audit artifacts for public use.

Related papers

• NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment [54.4265627247104]
  Large language models (LLMs) are increasingly used in peer review at major AI conferences.<n>Existing benchmarks assess novelty as a single holistic score.<n>We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis.
  arXiv  Detail & Related papers  (2026-09-10T08:34:56Z)
• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models [53.68149869349268]
  Large language models (LLMs) have shown growing potential for automated theoretical computer science (TCS) research.<n>We introduce ourbenchmark, an expert-validated benchmark for evaluating LLMs on frontier, end-to-end TCS research.
  arXiv  Detail & Related papers  (2026-08-20T15:13:41Z)
• When May a Model Replace the Experiment? Audits, Licenses, and the Price of Trust in Surrogate-Driven Design [8.037395295172088]
  Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensive evaluation.<n>Machine-learning surrogates that predict these outcomes are increasingly used to propose candidates but to grade them, and even to feed their own predictions back into the search as though they were measurements.<n>We establish when this practice is safe, what any certificate of safety must cost, and when the substitution provably pays.
  arXiv  Detail & Related papers  (2026-08-02T16:59:29Z)
• ConfidenceBench: Evaluating Confidence Calibration in Large Language Models [14.831793255747181]
  ConfidenceBench is a calibration benchmark for large language models.<n>It evaluates verbalized confidence estimates in 15 frontier large language models.<n> Confidence is elicited via prompting, requiring no access to model logits.
  arXiv  Detail & Related papers  (2026-07-10T01:56:30Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? [51.154921661608675]
  We introduce SoundnessBench, a curated benchmark of 1,099 machine-learning research proposals reconstructed from ICLR submissions.<n>SoundnessBench should be interpreted as a benchmark for recoverable proposal-stage soundness rather than exact prediction of full-paper review outcomes.
  arXiv  Detail & Related papers  (2026-05-28T17:57:37Z)
• HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam [63.84155758655084]
  Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models.<n>We introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy.<n>We evaluate seven state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points.
  arXiv  Detail & Related papers  (2026-02-15T02:50:15Z)
• Benchmark^2: Systematic Evaluation of LLM Benchmarks [66.2731798872668]
  We propose Benchmark2, a comprehensive framework comprising three complementary metrics.<n>We conduct experiments across 15 benchmarks spanning mathematics, reasoning, and knowledge domains.<n>Our analysis reveals significant quality variations among existing benchmarks and demonstrates that selective benchmark construction can achieve comparable evaluation performance.
  arXiv  Detail & Related papers  (2026-01-07T14:59:03Z)
• The NazoNazo Benchmark: A Cost-Effective and Extensible Test of Insight-Based Reasoning in LLMs [3.9977256267361754]
  We present Nazonazo, a cost-effective benchmark built from Japanese children's riddles to test insight-based reasoning.<n>No model except for GPT-5 is comparable to human performance, which achieves a 52.9% mean accuracy.
  arXiv  Detail & Related papers  (2025-09-18T07:50:04Z)
• Credal Two-Sample Tests of Epistemic Uncertainty [34.42566984003255]
  We introduce credal two-sample testing, a new hypothesis testing framework for comparing credal sets.<n>By generalising two-sample test to compare credal sets, our framework enables reasoning for equality, inclusion, intersection, and mutual exclusivity.
  arXiv  Detail & Related papers  (2024-10-16T18:09:09Z)
• Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias [33.99768156365231]
  We introduce a causal formulation for bias measurement in generative language models.<n>We propose a benchmark called OccuGender, with a bias-measuring procedure to investigate occupational gender bias.<n>The results show that these models exhibit substantial occupational gender bias.
  arXiv  Detail & Related papers  (2022-12-20T22:41:24Z)

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.