Persuasion in LLMs works by redirecting a small set of attention heads to copy the target option token instead of reasoning over evidence, via a rank-one routing feature that can be directly edited or removed.
Advances in neural information processing systems , volume=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.
citing papers explorer
-
How LLMs Are Persuaded: A Few Attention Heads, Rerouted
Persuasion in LLMs works by redirecting a small set of attention heads to copy the target option token instead of reasoning over evidence, via a rank-one routing feature that can be directly edited or removed.
-
Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
LLMs perform in-context learning as trajectories through a structured low-dimensional conceptual belief space, with the structure visible in both behavior and internal representations and causally manipulable via interventions.
-
Interpretability Can Be Actionable
Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.
-
Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers
Human visual interestingness is linearly decodable from final-layer embeddings in Qwen3-VL-8B and becomes progressively more structured across vision and language layers without explicit supervision.