Hugging Face Trending Papers
Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv AI
1d ago
Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations
The study examines how large language models (LLMs) repair code after runtime or API migrations, revealing that many repaired procedures run without errors yet produce incorrect results. Across 73 tasks and 60 documented changes in CPython, Node.js, and SQLite, the authors found that typical test inputs allowed 41% of wrong repairs to pass, while targeted edge inputs reduced this to 6–7%. Even with additional hard distractors and blind model writers, a significant fraction of incorrect repairs still passed the preregistered tests.
arXiv AI
Oct 16
Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair
The paper "Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair" investigates why large language model (LLM) code‑repair agents sometimes produce incorrect patches. By analyzing 1,844 model requests on two synthetic Python tasks—PersistQueue and Dijkstra—the authors trace how misconceptions in a model’s hypothesis or implementation plan lead to specific software obligation violations. They find that shifting a misconception from hypothesis to plan increases failure rates by roughly 30% for both tasks, revealing distinct, model‑dependent failure patterns linked to upstream misunderstandings.
arXiv AI
Sep 7
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.
arXiv AI
Oct 9
Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes
The paper investigates whether large language models (LLMs) can automatically verify no-code bug fixes—solutions that instruct users to change settings, upgrade versions, or alter workflows—by executing them in a real browser environment. Using 322 fixes from a benchmark, the study tests three executor agents (OpenCUA‑72B, Claude Sonnet 5, and Meta’s Muse Glimmer) and finds that only 17.6% of issues could be set up and passed sanity checks, with resolution rates ranging from 14.6% to 49.7% depending on the executor. Even the best configuration resolved fewer than half of the fixes, and executor choice significantly affected outcomes, highlighting the need for execution-based verification before such fixes reach users.
arXiv Machine Learning
Sep 10
Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them
arXiv:2609.05881v1 Announce Type: cross Abstract: Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution...
arXiv AI
Aug 25
PatchWrite: One Line, Not One Section -- Compile-Gated, Validity-Preserving Editing for AI-Drafted Manuscripts
arXiv:2608.23001v1 Announce Type: new Abstract: Automated manuscript pipelines often regenerate an entire section to repair a local defect, allowing unrelated metrics and citations to change even whe...