arXiv Machine Learning By Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh

Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models

Read the original on arXiv Machine Learning →

The paper introduces Janus, a method for validating error patterns in language models by comparing error rates across predefined yes/no properties and using shuffled decoy labels to set significance thresholds. Janus requires that a pattern’s error difference surpasses the decoy-derived threshold and is replicated on held‑out data before reporting. Experiments on a controlled code‑finding task confirm several meaningful error patterns, while on MuSiQue and LongBench v2 Janus reports no confirmed patterns for the tested properties, contrasting with standard shuffling tests that sometimes confirm patterns.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
1d ago

How Much Is Left Matters: False Positives and False Negatives in Partial-Prompt Contamination Tests

The paper evaluates partial‑prompt completion tests—where a model is given the first part of a benchmark problem and checked for reproducing the rest—on seven open‑weight models using MATH‑500 and recent AIME 2025/2026 problems as true negatives. It finds that memorization flags are highly sensitive to the amount of text left: problems with fewer than eight remaining words are flagged far more often than those with 25 or more, and most ROUGE‑based flags arise from short leftovers. On true negatives, even a high ROUGE‑L threshold flags up to 6.7% of problems at a 60% prefix, and exact‑match flags 8.6% at an 80% prefix, while models distilled from Qwen2.5‑Math show almost no recall of contamination. The authors recommend length‑stratified reporting, limiting prefixes to 60%, using style‑matched post‑cutoff controls, and cross‑family calibration to reduce false positives.

By Abhishek Anand
arXiv AI
6d ago

Agreeing on the Answer but Not the Reason: Measurement Limits of LLM Reasoning Failure Taxonomies

The paper investigates how failure taxonomies for large language model (LLM) reasoning can be misleading, focusing on a category called Compositional Collapse. By measuring this category across twelve models and eleven languages on a multilingual math benchmark, the authors find that the reported fraction of failures is highly sensitive to the order of classification tests and that human annotators rarely agree with the automated inspector on this category. They also show that the inspector’s labeling is largely driven by the prompt rather than the model itself, and that the category is over‑represented compared to native speaker judgments.

By Madhu Sudhan Rao Beesetty
arXiv Machine Learning
Oct 16

Causal Syntax Circuits in CodeLMs: Budget and Probe Decide What Looks Localised

The paper investigates whether the tendency of code language models to default to Python when no language is specified is driven by a small, identifiable set of internal components. Using a comprehensive pipeline—including ablation, activation patching, greedy circuit extraction, and significance testing—across 55 model-language configurations, the authors find that this preference is large, grows with model size, and persists after instruction tuning. They also show that the apparent localization of this behavior depends heavily on analysis choices such as component budget and probe design, and that interventions can sometimes alter the model’s output.

By Harsh Kumar, Tanmay Shailesh Joshi, Rahul Maity, Anusa Saha
arXiv AI
Oct 21

The More the Better? A Comparison of Single- and Multi-Agent LLM Setups on a Financial Review Task

The study compares single-agent and multi-agent large language model (LLM) setups for reviewing credit assessment memos against specified requirements. In a controlled experiment with 300 synthetic memos, a single agent examined six requirements in one call, while a team of three agents each checked two requirements. Results show the team identified 0.08 to 0.10 more defects on certain models but also produced more false alarms, used 2.2 to 2.4 times more tokens, and had mixed effects on balanced accuracy depending on instruction and model.

By Pei Liu