Memorization Over Reasoning? Exposing and Mitigating Verbatim Memorization in Large Language Models' Character Understanding Evaluation

• URL: http://arxiv.org/abs/2412.14368v5
• Date: Wed, 13 Aug 2025 13:44:46 GMT
• Title: Memorization Over Reasoning? Exposing and Mitigating Verbatim Memorization in Large Language Models' Character Understanding Evaluation
• Abstract summary: Large Language Models (LLMs) have shown impressive performance in character understanding tasks.<n>We argue that 'gist memory' should be the primary mechanism for character understanding tasks.<n>We introduce a simple yet effective method to mitigate mechanized memorization in character understanding evaluations.
• Score: 9.783129095443758
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, Large Language Models (LLMs) have shown impressive performance in character understanding tasks, such as analyzing the roles, personalities, and relationships of fictional characters. However, the extensive pre-training corpora used by LLMs raise concerns that they may rely on memorizing popular fictional works rather than genuinely understanding and reasoning about them. In this work, we argue that 'gist memory'-capturing essential meaning - should be the primary mechanism for character understanding tasks, as opposed to 'verbatim memory' - exact match of a string. We introduce a simple yet effective method to mitigate mechanized memorization in character understanding evaluations while preserving the essential implicit cues needed for comprehension and reasoning. Our approach reduces memorization-driven performance on popular fictional works from 96% accuracy to 72% and results in up to an 18% drop in accuracy across various character understanding tasks. These findings underscore the issue of data contamination in existing benchmarks, which often measure memorization rather than true character understanding.

Related papers

• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)
• Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs [14.925879394978852]
  Rote learning is a memorization technique based on repetition.<n>In this work, we demonstrate that LLMs can be trained to generalize from rote memorized data.
  arXiv  Detail & Related papers  (2025-07-29T15:28:41Z)
• Detecting Memorization in Large Language Models [0.0]
  Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data.<n>Traditional methods for detecting memorization rely on output probabilities or loss functions.<n>We introduce an analytical method that precisely detects memorization by examining neuron activations within the LLM.
  arXiv  Detail & Related papers  (2024-12-02T00:17:43Z)
• Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks [42.22616978679253]
  We introduce Sequence Order Recall Tasks (SORT), which we adapt from tasks used to study episodic memory in cognitive psychology. SORT requires LLMs to recall the correct order of text segments, and provides a general framework that is both easily extendable and does not require any additional annotations. Based on a human experiment with 155 participants, we show that humans can recall sequence order based on long-term memory of a book.
  arXiv  Detail & Related papers  (2024-10-10T17:17:38Z)
• Demystifying Verbatim Memorization in Large Language Models [67.49068128909349]
  Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. We develop a framework to study verbatim memorization in a controlled setting by continuing pre-training from Pythia checkpoints with injected sequences. We find that (1) non-trivial amounts of repetition are necessary for verbatim memorization to happen; (2) later (and presumably better) checkpoints are more likely to memorize verbatim sequences, even for out-of-distribution sequences.
  arXiv  Detail & Related papers  (2024-07-25T07:10:31Z)
• Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data [76.90128359866462]
  We introduce an extended concept of memorization, distributional memorization, which measures the correlation between the output probabilities and the pretraining data frequency.<n>We show that memorization plays a larger role in simpler, knowledge-intensive tasks, while generalization is the key for harder, reasoning-based tasks.
  arXiv  Detail & Related papers  (2024-07-20T21:24:40Z)
• Exploring Memorization in Fine-tuned Language Models [53.52403444655213]
  We conduct the first comprehensive analysis to explore language models' memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.
  arXiv  Detail & Related papers  (2023-10-10T15:41:26Z)
• Semantic HELM: A Human-Readable Memory for Reinforcement Learning [9.746397419479445]
  We propose a novel memory mechanism that represents past events in human language. We train our memory mechanism on a set of partially observable environments and find that it excels on tasks that require a memory component. Since our memory mechanism is human-readable, we can peek at an agent's memory and check whether crucial pieces of information have been stored.
  arXiv  Detail & Related papers  (2023-06-15T17:47:31Z)
• Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy [91.98116450958331]
  We argue that verbatim memorization definitions are too restrictive and fail to capture more subtle forms of memorization. Specifically, we design and implement an efficient defense that perfectly prevents all verbatim memorization. We conclude by discussing potential alternative definitions and why defining memorization is a difficult yet crucial open question for neural language models.
  arXiv  Detail & Related papers  (2022-10-31T17:57:55Z)
• Counterfactual Memorization in Neural Language Models [91.8747020391287]
  Modern neural language models that are widely used in various NLP tasks risk memorizing sensitive information from their training data. An open question in previous studies of language model memorization is how to filter out "common" memorization. We formulate a notion of counterfactual memorization which characterizes how a model's predictions change if a particular document is omitted during training.
  arXiv  Detail & Related papers  (2021-12-24T04:20:57Z)
• Learning to Rehearse in Long Sequence Memorization [107.14601197043308]
  Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning. Memory augmented neural networks introduce a human-like write-read memory to compress and memorize the long input sequence in one pass. But they have two serious drawbacks: 1) they continually update the memory from current information and inevitably forget the early contents; 2) they do not distinguish what information is important and treat all contents equally. We propose the Rehearsal Memory to enhance long-sequence memorization by self-supervised rehearsal with a history sampler.
  arXiv  Detail & Related papers  (2021-06-02T11:58:30Z)

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.