Memorization $\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition?

• URL: http://arxiv.org/abs/2509.04866v1
• Date: Fri, 05 Sep 2025 07:30:01 GMT
• Title: Memorization $\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition?
• Authors: Boxiang Ma, Ru Li, Yuanlong Wang, Hongye Tan, Xiaoli Li,
• Abstract summary: We propose a bi-perspective evaluation framework to assess large language models' scenario cognition.<n>We introduce a novel scenario-based dataset comprising diverse textual descriptions of fictional facts, annotated with scenario elements.<n>Our experiments reveal that current LLMs predominantly rely on superficial memorization, failing to achieve robust semantic scenario cognition.
• Score: 10.010113234203208
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Driven by vast and diverse textual data, large language models (LLMs) have demonstrated impressive performance across numerous natural language processing (NLP) tasks. Yet, a critical question persists: does their generalization arise from mere memorization of training data or from deep semantic understanding? To investigate this, we propose a bi-perspective evaluation framework to assess LLMs' scenario cognition - the ability to link semantic scenario elements with their arguments in context. Specifically, we introduce a novel scenario-based dataset comprising diverse textual descriptions of fictional facts, annotated with scenario elements. LLMs are evaluated through their capacity to answer scenario-related questions (model output perspective) and via probing their internal representations for encoded scenario elements-argument associations (internal representation perspective). Our experiments reveal that current LLMs predominantly rely on superficial memorization, failing to achieve robust semantic scenario cognition, even in simple cases. These findings expose critical limitations in LLMs' semantic understanding and offer cognitive insights for advancing their capabilities.

Related papers

• Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth [21.092167028989632]
  Drivelology is a linguistic phenomenon characterised by "nonsense with depth"<n>We construct a benchmark dataset of over 1,200+ meticulously curated and diverse examples across English, Mandarin, Spanish, French, Japanese, and Korean.<n>We find that current large language models (LLMs) consistently fail to grasp the layered semantics of Drivelological text.
  arXiv  Detail & Related papers  (2025-09-04T03:58:55Z)
• NeedleChain: Measuring Intact Long-Context Reasoning Capability of Large Language Models [7.134358758293254]
  The Needle-in-a-Haystack benchmark is widely used to evaluate Large Language Models' (LLMs) ability to understand long contexts (LC)<n>We demonstrate that even state-of-the-art models such as GPT-4o struggle to intactly incorporate given contexts made up of solely query-relevant ten sentences.<n>We introduce a novel benchmark, textbfNeedleChain, where the context consists entirely of query-relevant information.
  arXiv  Detail & Related papers  (2025-07-30T06:29:50Z)
• Metaphor and Large Language Models: When Surface Features Matter More than Deep Understanding [6.0158981171030685]
  This paper presents a comprehensive evaluation of the capabilities of Large Language Models (LLMs) in metaphor interpretation across multiple datasets, tasks, and prompt configurations.<n>We address these limitations by conducting extensive experiments using diverse publicly available datasets with inference and metaphor annotations.<n>The results indicate that LLMs' performance is more influenced by features like lexical overlap and sentence length than by metaphorical content.
  arXiv  Detail & Related papers  (2025-07-21T08:09:11Z)
• How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMs [13.822169295436177]
  We investigate how large language models (LLMs) process the temporal meaning of linguistic aspect in narratives that were previously used in human studies.<n>Our findings show that LLMs over-rely on prototypicality, produce inconsistent aspectual judgments, and struggle with causal reasoning derived from aspect.<n>These results suggest that LLMs process aspect fundamentally differently from humans and lack robust narrative understanding.
  arXiv  Detail & Related papers  (2025-07-18T18:28:35Z)
• Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey [54.90240495777929]
  Ambiguity remains a fundamental challenge in Natural Language Processing (NLP)<n>With the advent of Large Language Models (LLMs), addressing ambiguity has become even more critical due to their expanded capabilities and applications.<n>This paper explores the definition, forms, and implications of ambiguity for language driven systems.
  arXiv  Detail & Related papers  (2025-05-18T20:53:41Z)
• NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities [51.07379913779232]
  NeedleBench is a framework for assessing retrieval and reasoning performance in long-context tasks.<n>It embeds key data points at varying depths to rigorously test model capabilities.<n>Our experiments reveal that reasoning models like Deep-R1 and OpenAI's o3 struggle with continuous retrieval and reasoning in information-dense scenarios.
  arXiv  Detail & Related papers  (2024-07-16T17:59:06Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities.<n>If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information.<n>To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)
• 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)
• Uncertainty Quantification for In-Context Learning of Large Language Models [52.891205009620364]
  In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion.
  arXiv  Detail & Related papers  (2024-02-15T18:46:24Z)
• Can Large Language Models Understand Context? [17.196362853457412]
  This paper introduces a context understanding benchmark by adapting existing datasets to suit the evaluation of generative models. Experimental results indicate that pre-trained dense models struggle with understanding more nuanced contextual features when compared to state-of-the-art fine-tuned models. As LLM compression holds growing significance in both research and real-world applications, we assess the context understanding of quantized models under in-context-learning settings.
  arXiv  Detail & Related papers  (2024-02-01T18:55:29Z)
• MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations [37.13707912132472]
  Humans possess a remarkable ability to assign novel interpretations to linguistic expressions. Large Language Models (LLMs) have a knowledge cutoff and are costly to finetune repeatedly. We systematically analyse the ability of LLMs to acquire novel interpretations using in-context learning.
  arXiv  Detail & Related papers  (2023-10-18T00:02:38Z)
• Sentiment Analysis in the Era of Large Language Models: A Reality Check [69.97942065617664]
  This paper investigates the capabilities of large language models (LLMs) in performing various sentiment analysis tasks. We evaluate performance across 13 tasks on 26 datasets and compare the results against small language models (SLMs) trained on domain-specific datasets.
  arXiv  Detail & Related papers  (2023-05-24T10:45:25Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)

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.