Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

• URL: http://arxiv.org/abs/2507.00322v1
• Date: Mon, 30 Jun 2025 23:35:19 GMT
• Title: Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
• Authors: Daking Rai, Samuel Miller, Kevin Moran, Ziyu Yao,
• Abstract summary: Language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses.<n>Our study reveals that LMs rely on a number of components that independently make their own predictions.<n>We introduce RASteer, a steering method to systematically identify and increase the contribution of reliable components for improving model performance.
• Score: 13.381339115567288
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of these errors across LMs of varying sizes (124M-7B) to both understand and mitigate the errors. Our study reveals that LMs rely on a number of components (attention heads and FF neurons) that independently make their own predictions. While some components reliably promote correct answers across a generalized range of inputs (i.e., implementing "sound mechanisms''), others are less reliable and introduce noise by promoting incorrect tokens (i.e., implementing "faulty mechanisms''). Errors occur when the faulty mechanisms overshadow the sound ones and dominantly affect the predictions. Motivated by this insight, we introduce RASteer, a steering method to systematically identify and increase the contribution of reliable components for improving model performance. RASteer substantially improves performance on balanced parentheses tasks, boosting accuracy of some models from $0$% to around $100$% without impairing the models' general coding ability. We further demonstrate its broader applicability in arithmetic reasoning tasks, achieving performance gains of up to around $20$%.

Related papers

• Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models [68.57424628540907]
  Large language models (LLMs) often develop learned mechanisms specialized to specific datasets.<n>We introduce a fine-tuning approach designed to enhance generalization by identifying and pruning neurons associated with dataset-specific mechanisms.<n>Our method employs Integrated Gradients to quantify each neuron's influence on high-confidence predictions, pinpointing those that disproportionately contribute to dataset-specific performance.
  arXiv  Detail & Related papers  (2025-07-12T08:10:10Z)
• Language Models can perform Single-Utterance Self-Correction of Perturbed Reasoning [4.768151813962547]
  Large Language Models (LLMs) have demonstrated impressive mathematical reasoning capabilities.<n>Their performance remains brittle to minor variations in problem description and prompting strategy.<n>To better understand self-correction capabilities of recent models, we conduct experiments measuring models' ability to self-correct synthetics.
  arXiv  Detail & Related papers  (2025-06-18T21:35:44Z)
• GIM: Improved Interpretability for Large Language Models [23.12421433871512]
  Self-repair is a phenomenon where networks compensate for reduced signal in one component by amplifying others.<n>We introduce Gradient Interaction Modifications (GIM), a technique that accounts for self-repair during backpropagation.
  arXiv  Detail & Related papers  (2025-05-23T08:41:45Z)
• Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors [61.92704516732144]
  We show that the most robust features for correctness prediction are those that play a distinctive causal role in the model's behavior.<n>We propose two methods that leverage causal mechanisms to predict the correctness of model outputs.
  arXiv  Detail & Related papers  (2025-05-17T00:31:39Z)
• DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models [50.54264918467997]
  Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks.<n>Recent research has revealed that these models often rely on superficial features and shortcuts instead of developing a genuine understanding of language.<n>We propose Divergence Based Regularization (DBR) to mitigate this shortcut learning behavior.
  arXiv  Detail & Related papers  (2025-02-25T16:44:10Z)
• Understanding and Mitigating Classification Errors Through Interpretable Token Patterns [58.91023283103762]
  Characterizing errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors. We propose to discover those patterns of tokens that distinguish correct and erroneous predictions. We show that our method, Premise, performs well in practice.
  arXiv  Detail & Related papers  (2023-11-18T00:24:26Z)
• Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary [65.268245109828]
  Non-human-like behaviour of contemporary pre-trained language models (PLMs) is a leading cause undermining their trustworthiness. A striking phenomenon is the generation of inconsistent predictions, which produces contradictory results. We propose a practical approach that alleviates the inconsistent behaviour issue by improving PLM awareness.
  arXiv  Detail & Related papers  (2023-10-24T06:15:15Z)
• The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation [93.01964988474755]
  AutoMQM is a prompting technique which asks large language models to identify and categorize errors in translations. We study the impact of labeled data through in-context learning and finetuning. We then evaluate AutoMQM with PaLM-2 models, and we find that it improves performance compared to just prompting for scores.
  arXiv  Detail & Related papers  (2023-08-14T17:17:21Z)
• Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism [27.09416337926635]
  Current mainstream models often struggle with effectively utilizing word-level features and phonetic information. This paper introduces a novel approach that incorporates a dynamic error scaling mechanism to detect and correct phonetically erroneous text.
  arXiv  Detail & Related papers  (2023-08-07T09:19:59Z)
• Causal Disentanglement Hidden Markov Model for Fault Diagnosis [55.90917958154425]
  We propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism. Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors. To expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments.
  arXiv  Detail & Related papers  (2023-08-06T05:58:45Z)
• On the Efficacy of Generalization Error Prediction Scoring Functions [33.24980750651318]
  Generalization error predictors (GEPs) aim to predict model performance on unseen distributions by deriving dataset-level error estimates from sample-level scores. We rigorously study the effectiveness of popular scoring functions (confidence, local manifold smoothness, model agreement) independent of mechanism choice.
  arXiv  Detail & Related papers  (2023-03-23T18:08:44Z)

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.