SWEET: Mitigating Spurious Feature Reliance in LLM Reasoning via Weight Editing
cs.CL, cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models
- Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- SEAL: Steerable Reasoning Calibration of Large Language Models for Free
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Beyond Accuracy: Decomposing the Reasoning Efficiency of LLMs
- Steer2Edit: From Activation Steering to Component-Level Editing
- Kimi K3: Open Frontier Intelligence
- Steering Language Models With Activation Engineering
- Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
- Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation
- Chain of Draft: Thinking Faster by Writing Less
- Qwen3 Technical Report
- Uncovering Latent Chain of Thought Vectors in Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data