# Plausibility as Commonsense Reasoning: Humans Succeed, Large Language Models Do not

arXiv: https://arxiv.org/abs/2604.04825 · HTML: https://mlsanity.com/paper/2604.04825/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 6 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 16 of 16)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State](https://mlsanity.com/paper/1903.03260/) (2019)
- [A Benchmark for Systematic Generalization in Grounded Language Understanding](https://mlsanity.com/paper/2003.05161/) (2020)
- [Impact of Tokenization on Language Models: An Analysis for Turkish](https://mlsanity.com/paper/2204.08832/) (2022)
- [Forcing Diffuse Distributions out of Language Models](https://mlsanity.com/paper/2404.10859/) (2024)
- [Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens](https://mlsanity.com/paper/2304.11389/) (2023)
- [Syntactic Surprisal From Neural Models Predicts, But Underestimates, Human Processing Difficulty From Syntactic Ambiguities](https://mlsanity.com/paper/2210.12187/) (2022)
- [Multilingual Language Models Predict Human Reading Behavior](https://mlsanity.com/paper/2104.05433/) (2021)
- [Tokenization Standards for Linguistic Integrity: Turkish as a Benchmark](https://mlsanity.com/paper/2502.07057/) (2025)
- [Dougal Dil .Icslemede Tokenizasyon Standartlari ve "Olcc"um"u: T"urkcce "Uzerinden B"uy"uk Dil Modellerinin Karcsilacstirmali Analizi](https://mlsanity.com/paper/2508.13058/) (2025)
- [Who Relies More on World Knowledge and Bias for Syntactic Ambiguity Resolution: Humans or LLMs?](https://mlsanity.com/paper/2503.10838/) (2025)
- [Clause-Internal or Clause-External? Testing Turkish Reflexive Binding in Adapted versus Chain of Thought Large Language Models](https://mlsanity.com/paper/2602.00380/) (2026)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Source-Sensitive Reasoning in Turkish: Humans and LLMs under Evidential Trust Manipulation](https://mlsanity.com/paper/2604.24665/) (2026)

## Abstract (arXiv)

Large language models achieve strong performance on many language tasks, yet it remains unclear whether they integrate world knowledge with syntactic structure in a human-like, structure-sensitive way during ambiguity resolution. We test this question in Turkish prenominal relative-clause attachment ambiguities, where the same surface string permits high attachment (HA) or low attachment (LA). We construct ambiguous items that keep the syntactic configuration fixed and ensure both parses remain pragmatically possible, while graded event plausibility selectively favors High Attachment vs. Low Attachment. The contrasts are validated with independent norming ratings. In a speeded forced-choice comprehension experiment, humans show a large, correctly directed plausibility effect. We then evaluate Turkish and multilingual LLMs in a parallel preference-based setup that compares matched HA/LA continuations via mean per-token log-probability. Across models, plausibility-driven shifts are weak, unstable, or reversed. The results suggest that, in the tested models, plausibility information does not guide attachment preferences as reliably as it does in human judgments, and they highlight Turkish RC attachment as a useful cross-linguistic diagnostic beyond broad benchmarks.