# Trick or Neat: Adversarial Ambiguity and Language Model Evaluation

arXiv: https://arxiv.org/abs/2506.01205 · HTML: https://mlsanity.com/paper/2506.01205/

## 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 (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [A Systematic Assessment of Syntactic Generalization in Neural Language Models](https://mlsanity.com/paper/2005.03692/) (2020)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [We're Afraid Language Models Aren't Modeling Ambiguity](https://mlsanity.com/paper/2304.14399/) (2023)
- [AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs](https://mlsanity.com/paper/2311.06753/) (2023)
- [Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models](https://mlsanity.com/paper/2405.09605/) (2024)
- [Language models align with human judgments on key grammatical constructions](https://mlsanity.com/paper/2402.01676/) (2024)
- [Event knowledge in large language models: the gap between the impossible and the unlikely](https://mlsanity.com/paper/2212.01488/) (2022)
- [Prompting Language Models for Linguistic Structure](https://mlsanity.com/paper/2211.07830/) (2022)
- [Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks](https://mlsanity.com/paper/2307.16630/) (2023)
- [Word Order Does Matter (And Shuffled Language Models Know It)](https://mlsanity.com/paper/2203.10995/) (2022)
- [Probing for Incremental Parse States in Autoregressive Language Models](https://mlsanity.com/paper/2211.09748/) (2022)
- [Localizing Lying in Llama: Understanding Instructed Dishonesty on True-False Questions Through Prompting, Probing, and Patching](https://mlsanity.com/paper/2311.15131/) (2023)
- [Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0](https://mlsanity.com/paper/2407.03005/) (2024)
- [Zero and Few-shot Semantic Parsing with Ambiguous Inputs](https://mlsanity.com/paper/2306.00824/) (2023)
- [Towards Building a Robust Toxicity Predictor](https://mlsanity.com/paper/2404.08690/) (2024)
- [Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA](https://mlsanity.com/paper/2211.07516/) (2022)
- [Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers](https://mlsanity.com/paper/2310.09925/) (2023)
- [ChatGPT vs Gemini vs LLaMA on Multilingual Sentiment Analysis](https://mlsanity.com/paper/2402.01715/) (2024)
- [Do LLMs Understand Ambiguity in Text? A Case Study in Open-world Question Answering](https://mlsanity.com/paper/2411.12395/) (2024)
- [VISA: An Ambiguous Subtitles Dataset for Visual Scene-Aware Machine Translation](https://mlsanity.com/paper/2201.08054/) (2022)
- [Systematic Literature Review: Computational Approaches for Humour Style Classification](https://mlsanity.com/paper/2402.01759/) (2024)
- [Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently](https://mlsanity.com/paper/2401.06640/) (2024)
- [Perception of Phonological Assimilation by Neural Speech Recognition Models](https://mlsanity.com/paper/2406.15265/) (2024)
- [Resolving Transcription Ambiguity in Spanish: A Hybrid Acoustic-Lexical System for Punctuation Restoration](https://mlsanity.com/paper/2402.03519/) (2024)

## Built on by (most cited first, 3 of 3)

- [Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2](https://mlsanity.com/paper/2509.23204/) (2025)
- [Can LLMs Detect Ambiguous Plural Reference? An Analysis of Split-Antecedent and Mereological Reference](https://mlsanity.com/paper/2510.04581/) (2025)
- [Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMs](https://mlsanity.com/paper/2609.39572/) (2026)

## 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.