paper-with-me

Papers

Can Language Models Be Tricked by Language Illusions? Easier with Syntax, Harder with Semantics

2023-11-02 · Yuhan Zhang, Edward Gibson, Forrest Davis

Language models (LMs) have been argued to overlap substantially with human beings in grammaticality judgment tasks. But when humans systematically make errors in language processing, should we expect LMs to behave like cognitive models of language and mimic human behavior? We answer this question by investigating LMs' more subtle judgments associated with "language illusions" -- sentences that are vague in meaning, implausible, or ungrammatical but receive unexpectedly high acceptability judgments by humans. We looked at three illusions: the comparative illusion (e.g. "More people have been to Russia than I have"), the depth-charge illusion (e.g. "No head injury is too trivial to be ignored"), and the negative polarity item (NPI) illusion (e.g. "The hunter who no villager believed to be trustworthy will ever shoot a bear"). We found that probabilities represented by LMs were more likely to align with human judgments of being "tricked" by the NPI illusion which examines a structural dependency, compared to the comparative and the depth-charge illusions which require sophisticated semantic understanding. No single LM or metric yielded results that are entirely consistent with human behavior. Ultimately, we show that LMs are limited both in their construal as cognitive models of human language processing and in their capacity to recognize nuanced but critical information in complicated language materials.

📄 PDF Abstract BibTeX arXiv:2311.01386

Code (1)

forrestdavis/languageillusions 공식 구현

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Enhancing Generalization in Natural Language Inference by Syntax

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Qi He, Han Wang, Yue Zhang

Pre-trained language models such as BERT have achieved the state-of-the-art performance on natural language inference (NLI). However, it has been shown that such models can be tricked by variations of surface patterns su…

Natural Language InferenceSentence

The Illusion-Illusion: Vision Language Models See Illusions Where There are None

2024-12-07 · Tomer Ullman

Illusions are entertaining, but they are also a useful diagnostic tool in cognitive science, philosophy, and neuroscience. A typical illusion shows a gap between how something "really is" and how something "appears to be…

DiagnosticPhilosophy

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?

2023-10-31 · Yichi Zhang, Jiayi Pan, Yuchen Zhou, Rui Pan 외

Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human's perception of reality isn't always faithful to th…

IllusionBench: A Large-scale and Comprehensive Benchmark for Visual Illusion Understanding in Vision-Language Models

2025-01-01 · Yiming Zhang, ZiCheng Zhang, Xinyi Wei, Xiaohong Liu 외

Current Visual Language Models (VLMs) show impressive image understanding but struggle with visual illusions, especially in real-world scenarios. Existing benchmarks focus on classical cognitive illusions, which have bee…

HallucinationMultiple-choice

Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies

2026-02-02 · Wenjin Hou, Wei Liu, Han Hu, Xiaoxiao Sun 외 arxiv

Multimodal Large Language Models (MLLMs) have shown remarkable proficiency on general-purpose vision-language benchmarks, reaching or even exceeding human-level performance. However, these evaluations typically rely on s…

Visual Reasoning