Understanding the Repeat Curse in Large Language Models from a Feature Perspective

• URL: http://arxiv.org/abs/2504.14218v1
• Date: Sat, 19 Apr 2025 07:53:37 GMT
• Title: Understanding the Repeat Curse in Large Language Models from a Feature Perspective
• Authors: Junchi Yao, Shu Yang, Jianhua Xu, Lijie Hu, Mengdi Li, Di Wang,
• Abstract summary: Large language models (LLMs) often suffer from repetitive text generation.<n>We propose a novel approach, "Duplicatus Charm", to induce and analyze the Repeat Curse.
• Score: 10.413608338398785
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have made remarkable progress in various domains, yet they often suffer from repetitive text generation, a phenomenon we refer to as the "Repeat Curse". While previous studies have proposed decoding strategies to mitigate repetition, the underlying mechanism behind this issue remains insufficiently explored. In this work, we investigate the root causes of repetition in LLMs through the lens of mechanistic interpretability. Inspired by recent advances in Sparse Autoencoders (SAEs), which enable monosemantic feature extraction, we propose a novel approach, "Duplicatus Charm", to induce and analyze the Repeat Curse. Our method systematically identifies "Repetition Features" -the key model activations responsible for generating repetitive outputs. First, we locate the layers most involved in repetition through logit analysis. Next, we extract and stimulate relevant features using SAE-based activation manipulation. To validate our approach, we construct a repetition dataset covering token and paragraph level repetitions and introduce an evaluation pipeline to quantify the influence of identified repetition features. Furthermore, by deactivating these features, we have effectively mitigated the Repeat Curse.

Related papers

• Reasoning on Multiple Needles In A Haystack [9.765859280987053]
  We tackle the memory-based answering problem by filtering out direct-answer questions. We build on this insight to introduce a reflection mechanism for multi-round extension. We train a model using the generated iterative thinking process, which helps mitigate the performance degradation.
  arXiv  Detail & Related papers  (2025-04-05T11:58:08Z)
• Mitigating Copy Bias in In-Context Learning through Neuron Pruning [74.91243772654519]
  Large language models (LLMs) have demonstrated impressive few-shot in-context learning abilities. They are sometimes prone to a copying bias', where they copy answers from provided examples instead of learning the underlying patterns. We propose a novel and simple method to mitigate such copying bias.
  arXiv  Detail & Related papers  (2024-10-02T07:18:16Z)
• Detecting, Explaining, and Mitigating Memorization in Diffusion Models [49.438362005962375]
  We introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions. Our proposed method seamlessly integrates without disrupting sampling algorithms, and delivers high accuracy even at the first generation step. Building on our detection strategy, we unveil an explainable approach that shows the contribution of individual words or tokens to memorization.
  arXiv  Detail & Related papers  (2024-07-31T16:13:29Z)
• RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation [42.82192656794179]
  Large Language Models (LLMs) exhibit remarkable capabilities but are prone to generating inaccurate or hallucinatory responses. This limitation stems from their reliance on vast pretraining datasets, making them susceptible to errors in unseen scenarios. Retrieval-Augmented Generation (RAG) addresses this by incorporating external, relevant documents into the response generation process.
  arXiv  Detail & Related papers  (2024-03-31T08:58:54Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective [91.14291142262262]
  This work presents a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Our experiments reveal that penalizing the repetitions in training data remains critical even when considering larger model sizes and instruction tuning.
  arXiv  Detail & Related papers  (2023-10-16T09:35:42Z)
• Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation [92.42032403795879]
  We show that pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts. We attribute their overestimation of token-level repetition probabilities to the learning bias. We find that LMs use longer-range dependencies to predict repetitive tokens than non-repetitive ones, which may be the cause of sentence-level repetition loops.
  arXiv  Detail & Related papers  (2023-07-04T07:53:55Z)
• Joint Repetition Suppression and Content Moderation of Large Language Models [4.9990392459395725]
  Natural language generation (NLG) is one of the most impactful fields in NLP. In this paper, we apply non-exact repetition suppression using token and sequence level unlikelihood loss. We also explore the framework of unlikelihood training objective in order to jointly endow the model with abilities to avoid generating offensive words.
  arXiv  Detail & Related papers  (2023-04-20T19:17:49Z)
• Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation [102.25240608024063]
  Referring image segments an image from a language expression. We develop an algorithm that shifts from being localization-centric to segmentation-language. Compared to its counterparts, our method is more versatile yet effective.
  arXiv  Detail & Related papers  (2023-03-11T08:42:40Z)

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.