cs.CLNov 7, 2026

SWEET: Mitigating Spurious Feature Reliance in LLM Reasoning via Weight Editing

Authors: Zhizhang Fu, Lucas Zhao, Michalis Korakakis, Mengru Ding, Lukasz Szpruch, Yue Zhang

Organizations: Westlake University · Yale University · University of Cambridge · The Alan Turing Institute · 

Abstract

Reasoning in large language models can be disrupted by simple input perturbations (e.g. adding irrelevant distractors), suggesting reliance on spurious correlations. Identifying and suppressing the spurious features involved in long chain-of-thought reasoning remains challenging. We introduce Spurious-feature WEight EdiTing (SWEET), a training-free method that combines counterfactual interventions with mechanistic interpretability to identify and suppress spurious-features. SWEET extracts token- and sequence-level behavioral directions from activation contrasts between original problems and their counterfactual variants - capturing local and global patterns of spurious reasoning. It then localizes the responsible MLP neurons and attention heads and suppresses their contributions along these directions through weight edits. Using only 20 original-counterfactual pairs for direction extraction, SWEET improves accuracy by an average of 11.8 percentage points on perturbed inputs and 2 points on original inputs across five open-weight reasoning models and five reasoning benchmarks. It also reduces the relative gap between original and perturbed accuracies from 17.6% to 2.5%. Analyses identify two recurring forms of spurious reasoning, i.e. over-integrating irrelevant conditions and overthinking, and provide mechanistic evidence that SWEET improves reasoning robustness by suppressing both behavioral directions.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jan 12, 2026

Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models

Chain-of-Thought (CoT) prompting often improves the reasoning performance of large language models (LLMs), but the internal signal that triggers this behavior remains poorly understood. Leveraging the sparse features captured by Sparse Autoencoders (SAEs), we propose a systematic framework to analyze and intervene on the internal representations of LLMs, identifying a small set of latent features that are linked to reasoning behavior and can be causally tested through targeted intervention. Across multiple model families and reasoning benchmarks, we show that steering one or a small number of reasoning-related latent features can substantially induce reasoning behavior without explicit CoT prompting, achieving accuracy comparable to CoT. We further show that the identified features are not tied to particular wording patterns or verbosity, and confirm their causal role in reasoning through suppression experiments that impair performance even under CoT prompting. These results suggest that CoT prompting activates specific latent features to trigger reasoning, and that targeted intervention on these features offers an alternative pathway to elicit efficient reasoning behavior without explicit CoT prompting. Code is available at https://github.com/Zhenghao-He/LatentCoT.
Mar 21, 2026

Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach

Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a gradient-aware framework that detects and mitigates shortcut-promoting samples via ShortcutScore and gradient surgery. Our method identifies shortcut signals through gradient misalignment with validation objectives and answer-token concentration, and modifies training dynamics accordingly. Experiments on controlled reasoning benchmarks show that SART achieves +16.5% accuracy and +40.2% robustness over the strongest baseline, significantly improving generalization under distribution shifts. Code is available at: https://github.com/fuyanjie/short-cut-aware-data-centric-reasoning.
Oct 14, 2026

To Reason but Not to Stop: Understanding and Recovering Pruned Large Reasoning Models

Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much of this degradation stems from a failure to stop rather than to reason. As sparsity increases, pruned LRMs increasingly fail to terminate within the token budget, often after the correct answer has appeared in their reasoning, instead falling into repetitive loops, even though they still recognize where the dense model would stop. We further find that the hidden-state difference between terminating and looping continuations is consistent across pruned checkpoints, suggesting a shared direction associated with committing to an answer. Building on this, we propose Termination-Guided Activation Steering (TGAS), a training-free method that adds this direction to the residual stream at inference time. Across six LRMs, three pruning pipelines, and math and code benchmarks, TGAS improves termination and overall accuracy while reducing repetitive reasoning and generation length, showing that this failure is actionable.