{"slug": "detect-before-you-disambiguate-perturbation-based-input-ambiguity-detection-in", "title": "Detect Before You Disambiguate: Perturbation-Based Input Ambiguity Detection in LLMs", "summary": "A new arXiv paper (2610.36353v1) proposes a label-preserving perturbation framework for detecting ambiguous inputs to large language models before the models attempt to answer them. The authors instantiate the framework with two detectors — a black-box rule-based perturbation library and a white-box importance-guided method using model-internal signals — and report that across four datasets spanning open-domain, conversational and visual QA, both outperform output-side uncertainty baselines and LLM-paraphrase-based perturbation baselines. The work argues that ambiguity must be detected before disambiguation, since LLM-generated clarifications can resolve the ambiguity before it is measured, and the code is released on GitHub.", "body_md": "arXiv:2610.36353v1 Announce Type: new \nAbstract: Large language models (LLMs) often answer ambiguous inputs as if they had a single intended meaning. This is problematic because input ambiguity is an upstream source of uncertainty: when a prompt admits multiple valid interpretations, the key question is whether the model should answer directly at all. Existing input uncertainty methods often rely on LLM-generated statements or clarifications, but such transformations may already disambiguate the input before the ambiguity is measured. We propose a label-preserving perturbation framework for input ambiguity detection in which perturbations remain close to the original input while preserving its label. We instantiate this principle with two detectors: a black-box rule-based perturbation library and a white-box importance-guided method using model-internal signals. Experiments across four datasets in open-domain, conversational, and visual QA show that our methods outperform output-side uncertainty baselines and LLM-paraphrase-based perturbation baselines. Our results highlight the importance of detecting ambiguity before attempting to disambiguate it. Our code is available \\href{https://github.com/Xiao0o0o/input-ambiguity-detection}{\\textcolor{purple}{here}}.", "url": "https://wpnews.pro/news/detect-before-you-disambiguate-perturbation-based-input-ambiguity-detection-in", "canonical_source": "https://arxiv.org/abs/2610.36353", "published_at": "2026-10-28 04:00:00+00:00", "updated_at": "2026-10-28 04:12:45.298269+00:00", "lang": "en", "topics": ["large-language-models", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["arXiv", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/detect-before-you-disambiguate-perturbation-based-input-ambiguity-detection-in", "markdown": "https://wpnews.pro/news/detect-before-you-disambiguate-perturbation-based-input-ambiguity-detection-in.md", "text": "https://wpnews.pro/news/detect-before-you-disambiguate-perturbation-based-input-ambiguity-detection-in.txt", "jsonld": "https://wpnews.pro/news/detect-before-you-disambiguate-perturbation-based-input-ambiguity-detection-in.jsonld"}}