AMLworld-Compact introduces an importance‑weighted downsampling protocol for evaluating large language models on AMLworld’s test splits, retaining all illicit transactions while sampling benign ones from supervised‑score strata. The HT‑Coreset method reduces evaluation targets by 271× on HI‑Small and 611× on LI‑Small, providing unbiased confusion‑count estimates with exact recall and ratio estimates for precision and F1. Experiments with boosted‑tree strata and Graph Feature Preprocessor features show lower F1 RMSE compared to uniform sampling, and audit tools reveal that lexical checks do not reliably indicate correctness of model outputs.
By Natapong Nitarach, Phume Ngampornsukswadi, Pittawat Taveekitworachai, Surapon Nonesung, Warit Sirichotedumrong, Kunat Pipatanakul
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.
By Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh
The paper investigates the reliability of tool‑using agents, focusing on two failure modes: selecting the wrong tool and constructing incorrect arguments. It introduces a correct‑invocation rate metric to distinguish these errors and evaluates five open‑weight models on multi‑step tasks up to depth 8, finding that by depth 6 about 70% of a model’s clean‑context capability is lost due to earlier mistakes. The study reveals that exact‑match scoring against a fixed gold trajectory forces severity and recovery parameters to extreme values, and proposes a conditional‑on‑state scoring remedy that yields more realistic severity estimates.
By Afiya Noorain, Subhranshu Mohanty, Amritesh Banerjee, Abhijit Dasgupta
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: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.
By Jian Xu, Delu Zeng, John Paisley, Qibin Zhao
The study investigates whether open‑weight language models can introspect on their own internal computations. Using the Open‑Weight Masked Introspection (OWMI) framework, researchers intervened on various internal components of eight models and asked them to report whether changes had occurred. Across 78,000 measurements, none of the models reliably distinguished real interventions from sham ones, with AUROC values essentially at chance.
Why It Matters: The findings suggest that current open‑weight models lack the ability to audit their own internal states, highlighting a limitation for oversight that relies on a model’s self‑reporting.
By Emilio Ferrara
The study examined 305 quantized large language models (LLMs) from public registries, testing them on a 15‑task code screen and 164 HumanEval+ tasks. Only seven low‑bit, small‑parameter models failed to solve more than six tasks, and none of the files were corrupted—reproducibility did not guarantee functionality. The authors released audit data and a tool, recommending pre‑publication screening and calibration of low‑bit tags.
By Aditi Patodiya
The paper investigates whether large language models’ reasoning traces truly contain early, informative signals or merely reflect budget and difficulty confounds. Using a restart‑controlled truncation probe, the authors compare continuation success rates against from‑scratch restart curves across 178 problem‑model pairs, finding that only one case shows prefix‑limited success and that continuing a model’s own prefix generally outperforms restarting. A difficulty‑controlled test and two generation‑free analyses reveal that early internal signals do not carry outcome information beyond a problem‑difficulty baseline, underscoring the need for proper counterfactual controls.
By Yigit Utku Bulut
The paper evaluates Laya, a small model that processes a multiple‑choice question, its options, and a text in a single 512‑token sequence. Experiments show that when the relevant evidence lies beyond the window, accuracy drops to about 26–27%, and confidence metrics fail to warn of truncation. Fine‑tuning on longer documents improves performance on visible evidence but not on cut evidence, and a larger window or a 312‑token scan can yield modest gains.
By Mohammed Nayeem Khan, Allan Kevin T
arXiv:2607. 06636v1 Announce Type: cross Abstract: Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification-defined corner conditions.
By Amin Haeri, Mahdi Ghelichi
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
By Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh
The paper investigates where post‑training quantization (PTQ) harms large language models (LLMs) and how to best allocate a limited precision budget. By causally raising each layer to 8‑bit precision across nine open‑weight models, the authors find that quantization damage is diffuse rather than concentrated in specific task circuits or weight statistics, and that globally refining quantization granularity outperforms selectively protecting the most recoverable layers. They also observe that the residual accuracy loss is budget‑limited and that peak recovery locations correlate with architecture within families but not across families.
By Jundong Hu, Shekar Ramachandran