Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models
cs.CL, cs.AI
Submitted: 2026-01-12
Updated: 2026-08-31
Comments: Accepted at EMNLP' 2026 Main Conference
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them
- Training Verifiers to Solve Math Word Problems
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Temporal Predictors of Outcome in Reasoning Language Models
- Gemma 3 Technical Report
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- Qwen3 Technical Report
- Improving LLM Reasoning through Interpretable Role-Playing Steering
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering