Vision-language models (VLMs) can recognize entities in clear images yet still fail when answering questions that require factual knowledge beyond what is directly observable. Prior work has either examined individual failure modes in isolation or treated incorrect answers as monolithic, binary failures. We propose a tree-structured framework that organizes failures in knowledge-intensive visual question answering into model-specific operational outcomes. Across two datasets and four VLMs, we observe consistent distributions of operational outcomes: some failures occur before entity recognition, while others persist after the relevant entity is recognized. Visual token representations are most informative for recognition-related decisions. Prompt hidden states predict answer success more effectively, although factual-access attribution remains difficult and exhibits only a weak signal. These pre-generation signals support attribution-guided routing to targeted interventions, including image repair, entity support, question rewriting, and factual evidence.
K. Vo, Artem Vazhentsev, Artem Shelmanov et al.· 0 citations
Large language models (LLMs) frequently produce source code that seems correct and well-formed, yet includes hallucinated elements that cause downstream test failures. In this study, we benchmark state-of-the-art uncertainty quantification methods and existing base-lines for the task of hallucination detection in source code and introduce a diff-based pipeline to construct a code dataset annotated with line-level hallucinations. Building on this, we train a lightweight Transformer-based detector that uses LLM internal representations to identify hallucinations, substantially outperforming existing methods across several code generation domains. The detector also shows particular promise for enabling self-correction in LLM-based coding agents. We release the first publicly available dataset of line-level code hallucinations, along with the corresponding source code and trained hallucination detectors https://github.com/ datapaf/CodeHallucinationDetection
G. Andriushchenko, Roman Garaev, L. Rvanova et al.· Annual Meeting of the Associ...· 0 citations
An extensive experimental study is presented demonstrating that ARMT-augmented models process inputs well beyond their original context limits without degrading performance relative to in-limit baselines and need 30% less FLOPs while preserving baseline performance within the original context window.
Gleb Kuzmin, I. Rodkin, A. Bulatov et al.· 0 citations
