Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark

• URL: http://arxiv.org/abs/2608.04670v1
• Date: Wed, 05 Aug 2026 10:28:51 GMT
• Title: Easy to Complete, Hard to Choose: Investigating LLM Performance on the ProverbIT Benchmark
• Abstract summary: This paper introduces ProverbIT, a novel Italian benchmark comprising 100 multiple-choice questions designed to evaluate Large Language Models (LLMs)<n>We assess 13 frontier models, including Large Reasoning Models (LRMs) and traditional LLMs, across three tasks: proverb completion, multiple-choice selection with correct answers, and multiple-choice selection without correct answers.<n>Our evaluation reveals surprising results: while nearly all models demonstrate knowledge of the proverbs through successful completion tasks, performance drops dramatically when transitioning to multiple-choice formats without correct answers.
• Score: 3.899675786340556
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have transformed computational linguistics and achieved remarkable performance across numerous natural language processing tasks, yet significant gaps persist in understanding how these systems process culturally embedded linguistic expressions. This paper introduces ProverbIT, a novel Italian benchmark comprising 100 multiple-choice questions designed to evaluate LLMs' ability to complete Italian proverbs. We assess 13 frontier models, including Large Reasoning Models (LRMs) and traditional LLMs, across three tasks: proverb completion, multiple-choice selection with correct answers, and multiple-choice selection without correct answers. Our evaluation reveals surprising results: while nearly all models demonstrate knowledge of the proverbs through successful completion tasks, performance drops dramatically when transitioning to multiple-choice formats without correct answers, with even state-of-the-art reasoning models showing substantial degradation. Through detailed Chain-of-Thought analysis of two LRMs, we uncover that models exhibit a strong bias toward selecting literal synonyms and frequently mention correct proverb endings during reasoning without successfully identifying their absence from the given options. These findings suggest that current LLMs rely heavily on memorized patterns rather than deeper semantic understanding of culturally grounded expressions, highlighting important limitations in their reasoning capabilities for figurative language comprehension.

Related papers

• mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning [74.97363626515236]
  We propose a textbfMultilingual and Scalable Benchmark for textbfSkill-based textbfCommonsense textbfReasoning (textbfmSCoRe)<n>Our benchmark incorporates three key components that are designed to systematically evaluate LLM's reasoning capabilities.<n>Our results reveal the limitations of such reasoning-reinforced models when confronted with nuanced multilingual general and cultural commonsense.
  arXiv  Detail & Related papers  (2025-08-13T18:59:02Z)
• Language Matters: How Do Multilingual Input and Reasoning Paths Affect Large Reasoning Models? [59.970391602080205]
  Despite multilingual training, LRMs tend to default to reasoning in high-resource languages at test time.<n>Cultural reasoning degrades performance on reasoning tasks but benefits cultural tasks, while safety evaluations exhibit language-specific behavior.
  arXiv  Detail & Related papers  (2025-05-23T02:46:18Z)
• Do Large Language Models Excel in Complex Logical Reasoning with Formal Language? [20.53475791645822]
  Large Language Models (LLMs) have been shown to achieve breakthrough performance on complex logical reasoning tasks.<n>This paper aims to conduct a comprehensive evaluation of LLMs across various logical reasoning problems utilizing formal languages.
  arXiv  Detail & Related papers  (2025-05-22T17:57:23Z)
• On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation [12.848952248427977]
  Retrieval-augmented generation (RAG) with large language models (LLMs) has demonstrated strong performance in multilingual question-answering tasks.<n>In multilingual RAG, retrieved passages can be written in languages other than that of the query entered by the user.
  arXiv  Detail & Related papers  (2025-04-01T09:55:23Z)
• Can Large Language Models Identify Authorship? [16.35265384114857]
  Large Language Models (LLMs) have demonstrated an exceptional capacity for reasoning and problem-solving. This work seeks to address three research questions: (1) Can LLMs perform zero-shot, end-to-end authorship verification effectively? (2) Are LLMs capable of accurately attributing authorship among multiple candidates authors (e.g., 10 and 20)?
  arXiv  Detail & Related papers  (2024-03-13T03:22:02Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Models [34.22393697176282]
  We propose the Meta-Reasoning to broaden symbolic methods' applicability and adaptability in the real world. This method empowers LLMs to deconstruct reasoning-independent semantic information into generic symbolic representations. We conduct extensive experiments on more than ten datasets encompassing conventional reasoning tasks like arithmetic, symbolic, and logical reasoning, and the more complex interactive reasoning tasks like theory-of-mind reasoning.
  arXiv  Detail & Related papers  (2023-06-30T17:38:10Z)
• Improving Factuality and Reasoning in Language Models through Multiagent Debate [95.10641301155232]
  We present a complementary approach to improve language responses where multiple language model instances propose and debate their individual responses and reasoning processes over multiple rounds to arrive at a common final answer. Our findings indicate that this approach significantly enhances mathematical and strategic reasoning across a number of tasks. Our approach may be directly applied to existing black-box models and uses identical procedure and prompts for all tasks we investigate.
  arXiv  Detail & Related papers  (2023-05-23T17:55:11Z)
• Multilingual Large Language Models Are Not (Yet) Code-Switchers [41.47534626749588]
  Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks. The practice of alternating languages within an utterance remains relatively uncharted. We argue that current "multilingualism" in LLMs does not inherently imply proficiency with code-switching texts.
  arXiv  Detail & Related papers  (2023-05-23T16:50:48Z)
• Interpretable Unified Language Checking [42.816372695828306]
  We present an interpretable, unified, language checking (UniLC) method for both human and machine-generated language. We find that LLMs can achieve high performance on a combination of fact-checking, stereotype detection, and hate speech detection tasks.
  arXiv  Detail & Related papers  (2023-04-07T16:47:49Z)

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.