Solution Hacking is identified, a failure mode in which an LLM reaches the correct answer through invalid shortcuts, such as numerical search, enumeration, guessing, or answer-first verification, without providing a valid task-targeted derivation.
Abstract
Scientific reasoning benchmarks typically evaluate large language models (LLMs) using final-answer accuracy. However, a correct answer does not necessarily demonstrate the reasoning capability targeted by the problem. We identify Solution Hacking, a failure mode in which an LLM reaches the correct answer through invalid shortcuts, such as numerical search, enumeration, guessing, or answer-first verification, without providing a valid task-targeted derivation. We systematically analyze this phenomenon across difficulty levels, scientific domains, and frontier models. Solution hacking increases sharply with benchmark difficulty, from 2.2\% on common problems to 28.3\% on Olympiad-level problems and 37.4\% on HLE. Moreover, 8.2\%-44.1\% of answers credited as correct across frontier models are identified as hacked solutions. We further develop expert-inspired anti-hacking strategies, including an automatic judge and a test-time instruction. The results show that suppressing shortcut behavior substantially reduces reported accuracy while having a smaller effect on correct and non-hacked accuracy. These findings reveal that answer-only evaluation can overestimate the scientific reasoning capabilities of frontier LLMs.
Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final-answer accuracy. This can obscure whether a model can verify a non-canonical but valid solution trace. We introduce a controlled linear-equation benchmark for evaluating LLMs in the evaluator role. Each instance asks the model to judge final-answer correctness, step-level trace correctness, and the first incorrect step. Our evaluation of state-of-the-art open LLMs reveals a significant robustness gap: models that accurately evaluate canonical solutions often fail when presented with perturbed but logically equivalent variants. Across GPT-OSS 20B, Qwen3-14B, and Phi-4-Reasoning, base models perform well on canonical traces but degrade substantially on perturbed traces, especially for error localization. On valid perturbed traces, base-model false-rejection rates reach 75.6-85.3%, showing strong sensitivity to canonical solution form. Supervised fine-tuning, distillation, and test-time compute improve robustness in some settings, but gains are model dependent and can trade off against canonical performance. The results show that reliable process-level verification remains challenging, and evaluator robustness should be measured separately from solver accuracy, even in a simple algebraic domain with exact ground truth.
State-of-the-art models are far more proficient in scientific coding than SciCode has suggested---the bottleneck was not model capability, but the quality of the evaluation instrument.
Sihan Hu, Lyuhan Huang, You-Jin Deng et al.· 0 citations
A probe corpus of 42 retracted, fraudulent, and pseudoscientific papers is paired with a methodology for eliciting and scoring single-shot model engagement with each paper's framing, indicating an urgent need for guardrail infrastructure for scientific deployment of language models.
Large language models (LLMs) increasingly repair software vulnerabilities, but most evaluations judge only similarity to a developer fix or removal of the weakness. Neither reveals whether working code was broken. We evaluate eight commercial and open LLMs on 922 JavaScript vulnerability patches, scoring neutralisation and functional preservation. Lacking tests, we score at scale with a reference-based LLM judge, calibrated against execution on a 144-patch benchmark and 254 Java-CVE patches, plus a cross-family judge. The best model fixes 23% of vulnerabilities (judge-based), and cost-efficiency inverts the accuracy ranking. Our central finding concerns the instrument: both judges flag more over-fixes than execution confirms (precision 5–10%), yet on the functional axis agree far more with each other (κ=0.75) than with execution (κ≤0.26), so judge–judge agreement measures reliability, not validity. On real Java code the over-reporting persists, while the judges’ correctness estimates diverge, leaving no single judge trustworthy. Over-fixing is genuine but, under execution, uncommon: a few percent of vulnerability-removing patches, or under 2%, excluding one artefact-prone scenario, both lower bounds. Only adequately tested execution measures the functional-preservation rate, so security-patch evaluation must run the code, use a judge only to rank models, and weigh costs. We release the harness and executable benchmark.
Patrick Deininger, Wolfgang Slany· Journal of Cybersecurity and...· 0 citations
The Reasoning Answer Faithfulness Score (RAFS) is introduced, a reference free, instance level diagnostic of whether an emitted mathematical trace is locally credible, supports its answer, and is stable under resampling and targeted counterfactual interventions.
Vivek Shukla, Varun Shukla, Atul et al.· arXiv.org· 0 citations
The results indicate how trustworthy LLM-generated explanations are in model-free settings, where the same LLMs are used but no oracle exists to verify them.
Dennis Gross, Helge Spieker· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
