Trick or Neat: Adversarial Ambiguity and Language Model Evaluation

• URL: http://arxiv.org/abs/2506.01205v1
• Date: Sun, 01 Jun 2025 22:50:06 GMT
• Title: Trick or Neat: Adversarial Ambiguity and Language Model Evaluation
• Authors: Antonia Karamolegkou, Oliver Eberle, Phillip Rust, Carina Kauf, Anders Søgaard,
• Abstract summary: We assess language models' sensitivity to ambiguity by introducing an adversarial ambiguity dataset.<n>Our findings show that direct prompting fails to robustly identify ambiguity, while linear probes trained on model representations can decode ambiguity with high accuracy.
• Score: 42.62991342963119
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting ambiguity is important for language understanding, including uncertainty estimation, humour detection, and processing garden path sentences. We assess language models' sensitivity to ambiguity by introducing an adversarial ambiguity dataset that includes syntactic, lexical, and phonological ambiguities along with adversarial variations (e.g., word-order changes, synonym replacements, and random-based alterations). Our findings show that direct prompting fails to robustly identify ambiguity, while linear probes trained on model representations can decode ambiguity with high accuracy, sometimes exceeding 90\%. Our results offer insights into the prompting paradigm and how language models encode ambiguity at different layers. We release both our code and data: https://github.com/coastalcph/lm_ambiguity.

Related papers

• From Disagreement to Understanding: The Case for Ambiguity Detection in NLI [0.0]
  We show that content-based ambiguity offers a process-independent signal of divergent human perspectives.<n>A key limitation is the lack of annotated datasets for ambiguity and subtypes.<n>We propose addressing this gap through new annotated resources and unsupervised approaches to ambiguity detection.
  arXiv  Detail & Related papers  (2025-07-20T20:27:35Z)
• Análise de ambiguidade linguística em modelos de linguagem de grande escala (LLMs) [0.35069196259739965]
  Linguistic ambiguity continues to represent a significant challenge for natural language processing (NLP) systems. Inspired by the recent success of instructional models like ChatGPT and Gemini, this study aims to analyze and discuss linguistic ambiguity within these models.
  arXiv  Detail & Related papers  (2024-04-25T14:45:07Z)
• Zero and Few-shot Semantic Parsing with Ambiguous Inputs [45.285508941560295]
  We introduce AmP, a framework, dataset, and challenge for translating ambiguous natural language to formal representations like logic and code. Using AmP, we investigate how several few-shot text-to-code systems handle ambiguity, introducing three new metrics. We find that large pre-trained models perform poorly at capturing the distribution of possible meanings without deliberate instruction.
  arXiv  Detail & Related papers  (2023-06-01T15:46:36Z)
• We're Afraid Language Models Aren't Modeling Ambiguity [136.8068419824318]
  Managing ambiguity is a key part of human language understanding. We characterize ambiguity in a sentence by its effect on entailment relations with another sentence. We show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity.
  arXiv  Detail & Related papers  (2023-04-27T17:57:58Z)
• Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models [64.58271886337826]
  We study ambiguities that arise in text-to-image generative models. We propose a framework to mitigate ambiguities in the prompts given to the systems by soliciting clarifications from the user.
  arXiv  Detail & Related papers  (2022-11-17T17:12:43Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
  We propose a novel latent-variable formulation for constructing intrinsic probes.<n>We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
  arXiv  Detail & Related papers  (2022-01-20T15:01:12Z)
• Speakers Fill Lexical Semantic Gaps with Context [65.08205006886591]
  We operationalise the lexical ambiguity of a word as the entropy of meanings it can take. We find significant correlations between our estimate of ambiguity and the number of synonyms a word has in WordNet. This suggests that, in the presence of ambiguity, speakers compensate by making contexts more informative.
  arXiv  Detail & Related papers  (2020-10-05T17:19:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.