Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing

• URL: http://arxiv.org/abs/2410.17194v5
• Date: Wed, 11 Jun 2025 14:29:40 GMT
• Title: Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
• Authors: Kento Nishi, Rahul Ramesh, Maya Okawa, Mikail Khona, Hidenori Tanaka, Ekdeep Singh Lubana,
• Abstract summary: Knowledge Editing (KE) algorithms alter models' weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations.<n>We show that applying KE can adversely affect models' broader factual recall accuracy and diminish their reasoning abilities.<n>Our work yields a precise mechanistic hypothesis to explain why KE has adverse effects on model abilities.
• Score: 20.276952762837098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge Editing (KE) algorithms alter models' weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations. However, recent work has shown that applying KE can adversely affect models' broader factual recall accuracy and diminish their reasoning abilities. Although these studies give insights into the potential harms of KE algorithms, e.g., performance evaluations on benchmarks, little is understood about why such destructive failures occur. Motivated by this, we define a novel synthetic task in which a Transformer is trained from scratch to internalize a "structured" knowledge graph. The structure enforces relationships between entities of the graph, such that editing a factual association has "trickling effects" on other entities (e.g., altering X's parent is Y to Z affects who X's siblings' parent is). Through evaluations of edited models on this task, we show that KE inadvertently affects representations of entities beyond the targeted one, distorting relevant structures that allow a model to infer unseen knowledge about an entity. We call this phenomenon representation shattering and demonstrate that it degrades models' factual recall and reasoning performance. We further corroborate our findings in naturalistic settings with pre-trained Llama and Mamba models as well. Overall, our work yields a precise mechanistic hypothesis to explain why KE has adverse effects on model abilities.

Related papers

• Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers [76.42159902257677]
  We argue that both behaviors stem from a single mechanism known as out-of-context reasoning (OCR)<n>OCR drives both generalization and hallucination, depending on whether the associated concepts are causally related.<n>Our work provides a theoretical foundation for understanding the OCR phenomenon, offering a new lens for analyzing and mitigating undesirable behaviors from knowledge injection.
  arXiv  Detail & Related papers  (2025-06-12T16:50:45Z)
• The emergence of sparse attention: impact of data distribution and benefits of repetition [14.652502263025882]
  We study the emergence over training of sparse attention, a critical and frequently observed attention pattern in Transformers.<n>By combining theoretical analysis of a toy model with empirical observations on small Transformers trained on a linear regression variant, we uncover the mechanics sparse attention emergence.<n>Our findings provide a simple, theoretically grounded framework for understanding how data distributions and model design influence the learning dynamics behind one form of emergence.
  arXiv  Detail & Related papers  (2025-05-23T13:14:02Z)
• Do Larger Language Models Imply Better Reasoning? A Pretraining Scaling Law for Reasoning [89.17086632436363]
  We introduce a synthetic multihop reasoning environment designed to replicate the structure and distribution of real-world large-scale knowledge graphs. Our reasoning task involves completing missing edges in the graph, which requires advanced multi-hop reasoning and mimics real-world reasoning scenarios. To predict the optimal model size for a specific knowledge graph, we find an empirical scaling that linearly maps the knowledge graph search entropy to the optimal model size.
  arXiv  Detail & Related papers  (2025-04-04T17:57:22Z)
• DAG-aware Transformer for Causal Effect Estimation [0.8192907805418583]
  Causal inference is a critical task across fields such as healthcare, economics, and the social sciences. In this paper, we present a novel transformer-based method for causal inference that overcomes these challenges. The core innovation of our model lies in its integration of causal Directed Acyclic Graphs (DAGs) directly into the attention mechanism.
  arXiv  Detail & Related papers  (2024-10-13T23:17:58Z)
• "Why" Has the Least Side Effect on Model Editing [25.67779910446609]
  This paper delves into a critical factor-question type-by categorizing model editing questions. Our findings reveal that the extent of performance degradation varies significantly across different question types. We also examine the impact of batch size on side effects, discovering that increasing the batch size can mitigate performance drops.
  arXiv  Detail & Related papers  (2024-09-27T12:05:12Z)
• Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training [14.450673163785094]
  Context-Aware Emotion Recognition (CAER) provides valuable semantic cues for recognizing the emotions of target persons. Current approaches invariably focus on designing sophisticated structures to extract perceptually critical representations from contexts. We present a Contextual Causal Intervention Module (CCIM) to de-confound the confounder.
  arXiv  Detail & Related papers  (2024-07-06T05:29:02Z)
• A Theoretical Understanding of Self-Correction through In-context Alignment [51.622068973630796]
  Large language models (LLMs) are capable of improving their abilities purely by self-correction. We show that when LLMs give relatively accurate self-examinations as rewards, they are capable of refining responses in an in-context way. Inspired by these findings, we also illustrate applications of self-correction, such as defending against LLM jailbreaks.
  arXiv  Detail & Related papers  (2024-05-28T22:33:02Z)
• Understanding Emergent Abilities of Language Models from the Loss Perspective [32.81782726603632]
  We study emergent abilities in the lens of pre-training loss, instead of model size or training compute.<n>We find that a model exhibits emergent abilities on certain tasks regardless of the continuity of metrics.<n>This inspires us to redefine emergent abilities as those that manifest in models with lower pre-training losses.
  arXiv  Detail & Related papers  (2024-03-23T11:03:31Z)
• Counterfactual Image Editing [54.21104691749547]
  Counterfactual image editing is an important task in generative AI, which asks how an image would look if certain features were different. We formalize the counterfactual image editing task using formal language, modeling the causal relationships between latent generative factors and images. We develop an efficient algorithm to generate counterfactual images by leveraging neural causal models.
  arXiv  Detail & Related papers  (2024-02-07T20:55:39Z)
• Context De-confounded Emotion Recognition [12.037240778629346]
  Context-Aware Emotion Recognition (CAER) aims to perceive the emotional states of the target person with contextual information. A long-overlooked issue is that a context bias in existing datasets leads to a significantly unbalanced distribution of emotional states. This paper provides a causality-based perspective to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task.
  arXiv  Detail & Related papers  (2023-03-21T15:12:20Z)
• CLEAR: Generative Counterfactual Explanations on Graphs [60.30009215290265]
  We study the problem of counterfactual explanation generation on graphs. A few studies have explored counterfactual explanations on graphs, but many challenges of this problem are still not well-addressed. We propose a novel framework CLEAR which aims to generate counterfactual explanations on graphs for graph-level prediction models.
  arXiv  Detail & Related papers  (2022-10-16T04:35:32Z)
• Explainers in the Wild: Making Surrogate Explainers Robust to Distortions through Perception [77.34726150561087]
  We propose a methodology to evaluate the effect of distortions in explanations by embedding perceptual distances. We generate explanations for images in the Imagenet-C dataset and demonstrate how using a perceptual distances in the surrogate explainer creates more coherent explanations for the distorted and reference images.
  arXiv  Detail & Related papers  (2021-02-22T12:38:53Z)
• Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs [0.0]
  In RNNs, encoding information in a suboptimal way can impact the quality of representations based on later elements in the sequence. I propose an augmentation to standard RNNs in form of a gradient-based correction mechanism. I conduct different experiments in the context of language modeling, where the impact of using such a mechanism is examined in detail.
  arXiv  Detail & Related papers  (2021-01-03T17:54:17Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)
• CausalVAE: Structured Causal Disentanglement in Variational Autoencoder [52.139696854386976]
  The framework of variational autoencoder (VAE) is commonly used to disentangle independent factors from observations. We propose a new VAE based framework named CausalVAE, which includes a Causal Layer to transform independent factors into causal endogenous ones. Results show that the causal representations learned by CausalVAE are semantically interpretable, and their causal relationship as a Directed Acyclic Graph (DAG) is identified with good accuracy.
  arXiv  Detail & Related papers  (2020-04-18T20:09:34Z)
• A Critical View of the Structural Causal Model [89.43277111586258]
  We show that one can identify the cause and the effect without considering their interaction at all. We propose a new adversarial training method that mimics the disentangled structure of the causal model. Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
  arXiv  Detail & Related papers  (2020-02-23T22:52:28Z)

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.