Testing LLM-based software is expensive: each input needs several sampled responses, each judged by a costly oracle. Further, every prompt or model change calls for re-testing. Pre-generation adequacy...
arXiv:2509. 17314v4 Announce Type: replace-cross Abstract: Software increasingly relies on the emergent capabilities of Large Language Models (LLMs), from natural language understanding to program analysis and generation.
arXiv:2607. 11342v1 Announce Type: cross Abstract: Despite their central role in fault detection, test oracles remain challenging to construct effectively.
arXiv:2608.30581v1 Announce Type: new Abstract: Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an...
Large language models (LLMs) are used as post hoc explainers of sequential decision-making policies, producing natural-language explanations of why an action was chosen. However, LLMs often generate p...
arXiv:2606. 31630v1 Announce Type: new Abstract: Language models increasingly write probabilistic programs (in NumPyro, Stan, or Pyro), but a program that compiles, runs, and passes every unit test can still be \emph{statistically} wrong -- a Gaussian likelihood for heavy-tailed data, a Poisson for over-dispersed counts, an invalid prior support, or a pathological parameterization.
arXiv:2509. 14704v3 Announce Type: replace Abstract: Benchmark saturation and training-data contamination increasingly obscure whether reported gains in large language models (LLMs) reflect genuine advances in reasoning or familiarity with recurring patterns in benchmark problems.
arXiv:2608.22138v1 Announce Type: new Abstract: Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present...
The paper introduces RADAR, a framework for repairing and auditing confidence scores in large language models (LLMs). It separates confidence repair from deployment decisions and from error auditing, proposing Probe‑Anchored Isotonic Calibration (PAIC) for monotone mapping and a prompt‑clustered kernel test for detecting residual errors. Experiments across checkpoints and benchmarks show that richer predictors can improve confidence estimation, but projecting back to a scalar score can lose gains, and lower prediction risk does not always lead to better review decisions.
arXiv:2610.17747v1 Announce Type: cross Abstract: Failure-attribution benchmarks ask an LLM judge which step or agent caused a failure. A high score should mean the judge checked the faulty step agai...
arXiv:2607. 09999v1 Announce Type: cross Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved.
arXiv:2605.30018v3 Announce Type: replace-cross Abstract: Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of the...