arXiv Machine Learning

Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them

arXiv Computation and Language
Aug 31

Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models

The study investigates how language models equipped with tools can still produce unsupported final claims, even when a single tool call could resolve the uncertainty. It defines two metrics—occurrence (how often unsupported claims arise) and conditional repair (how often they are fixed when evidence is provided). Experiments on Qwen3-32B and Gemma 4 show that providing the missing evidence consistently repairs all unsupported claims in the Qwen3-32B setup, while the Gemma 4 model never produced unsupported claims under the tested conditions.

By Justin Bronder
arXiv AI
6d ago

Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair

The paper investigates hallucination in large language model–based automated program repair (APR). It defines hallucination as producing patches or intermediate artifacts that are not grounded in available repair evidence, and analyzes it across final patches and intermediate tasks such as triggering test case identification, line coverage prediction, and additional test case generation. Experiments on 832 Defects4J bugs show that only 21.0%–55.9% of patches pass the developer test suite, with 72.7% of sampled repairs exhibiting hallucinations, often due to incorrect causal localization or repair strategies.

By Xuemeng Cai, Jiakun Liu, Linhan Yang, Wei Ma, Lingxiao Jiang
arXiv AI
Sep 4

Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

The paper reports a preregistered audit of language‑model judges used as measurement instruments, revealing that the assumption that a model’s responses remain stable over time is invalid. Across nearly 53,000 audited requests, repeat rankings and byte‑identical replays fell far below required reliability thresholds, with three identified mechanisms—label‑to‑meaning bias, candidate gaps below the noise floor, and input permutation noise—explaining the discrepancy. The study proposes a three‑level snapshot‑identity framework, eight design rules, and a reporting checklist to prevent such reliability failures in future evaluations.

By Haoyaun Zhu, Jie Zhang
arXiv AI
Aug 24

Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol

The paper introduces a framework for evaluating how large language model agents revise their success criteria after failures, defining five non‑compensatory conditions that must be met for a criterion revision to be considered valid. Using the CMB‑0.1 protocol, the authors test twelve cross‑domain scenarios across four system configurations, finding that no model trial satisfies all five conditions and highlighting specific failure modes such as zero‑state reconstruction and inadequate intervention sensitivity. They propose a more stringent trace‑anchored CMB‑0.4 protocol to better isolate and measure criterion revision in future studies.

By Guodong Xu
arXiv AI
Aug 6

ORCA-bench: How Ready Are Language Model Agents for Oncall?

arXiv:2607. 28545v2 Announce Type: replace-cross Abstract: Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics, logs, traces, and source code, starting from ambiguous user-facing reports, often hours after the incident began.

By Albert Gong, Kyuseong Choi, Abhineet Agarwal, Jason Schechner, Ryan Huang, Raj Agrawal, Anish Agarwal, Raaz Dwivedi
Hugging Face Trending Papers
Sep 3

Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

The paper investigates the reliability of language‑model judges used as measurement instruments on shared endpoints. Through two preregistered audits of 52,988 requests, the authors found that repeat rankings and byte‑identical replays fell far short of required thresholds, revealing significant instability. They identify three mechanisms—label‑to‑meaning bias, candidate gaps below the noise floor, and input permutation noise—that explain the gap, and propose a snapshot‑identity ladder, design rules, and a reporting checklist to mitigate such failures.

arXiv AI
Sep 2

Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair

The study evaluates whether fault localization improves test‑guided code repair by comparing three approaches—blind whole‑solution resampling, spectrum‑based localized infilling, and random‑span infilling—across multiple large language models and benchmarks. Results show that localization is rarely available (only 9.0% of failing candidates), and when it is, localized infilling performs worse than blind resampling, with only suggestive evidence of a benefit over random spans. The findings suggest that targeted edits may not provide a consistent advantage over broader, untargeted repair attempts in current large‑model settings.

By Anik Jha