mlsanityData to 14 Oct 2026

Trick or Neat: Adversarial Ambiguity and Language Model Evaluation

arXiv 2506.01205 ↗First posted 1 Jun 2025cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

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/lmambiguity.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 58 references that are in the map. First posted on arXiv 1 Jun 2025.

Builds on

30 of 58 references.

References · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019BLiMP: The Benchmark of Linguistic Minimal Pairs for Englishcited by 564
  4. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
  5. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  6. 2016Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependenciescited by 354
  7. 2020A Systematic Assessment of Syntactic Generalization in Neural Language Modelscited by 165
  8. 2019Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic Statecited by 138
  9. 2023We're Afraid Language Models Aren't Modeling Ambiguitycited by 126
  10. 2023AudioChatLlama: Towards General-Purpose Speech Abilities for LLMscited by 59
  11. 2024Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Modelscited by 55
  12. 2024Language models align with human judgments on key grammatical constructionscited by 49
18 more
  1. 2022Event knowledge in large language models: the gap between the impossible and the unlikelycited by 45
  2. 2022Prompting Language Models for Linguistic Structurecited by 39
  3. 2023Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attackscited by 34
  4. 2022Word Order Does Matter (And Shuffled Language Models Know It)cited by 32
  5. 2022Probing for Incremental Parse States in Autoregressive Language Modelscited by 24
  6. 2023Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patchingcited by 24
  7. 2024Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0cited by 19
  8. 2023Zero and Few-shot Semantic Parsing with Ambiguous Inputscited by 16
  9. 2024Towards Building a Robust Toxicity Predictorcited by 14
  10. 2022Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQAcited by 13
  11. 2023Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformerscited by 13
  12. 2024ChatGPT vs Gemini vs LLaMA on Multilingual Sentiment Analysiscited by 13
  13. 2024Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answeringcited by 13
  14. 2022VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translationcited by 11
  15. 2024Systematic Literature Review: Computational Approaches for Humour Style Classificationcited by 6
  16. 2024Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistentlycited by 3
  17. 2024Perception of Phonological Assimilation by Neural Speech Recognition Modelscited by 3
  18. 2024Resolving Transcription Ambiguity in Spanish: A Hybrid Acoustic-Lexical System for Punctuation Restorationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2cited by 2
  2. 2025Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Referencecited by 0
  3. 2026Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs
  2. 2026Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution
  3. 2026Sensitivity Uncertainty Alignment in Large Language Models ↗
  4. 2024RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs
  5. 2026Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture
  6. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
  7. 2023Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations
  8. 2024Aligning Language Models to Explicitly Handle Ambiguity