A geometric decomposition framework shows that affine transformations best recover prompt-induced task geometry and behavior in language and vision models across multiple datasets.
Manning, and Christopher Potts
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Prompt-boundary directional alignment enables geometry-guided search that cuts trials to 95% best utility by 39.8% on average, while concept granularity predicts remaining difficulty via directional heterogeneity.
Memory Inception is a training-free method that injects latent KV banks at chosen layers to steer LLMs, achieving superior control-drift balance and up to 118x storage reduction on personality and structured-reasoning tasks.
MoCo supplies a unified library of 26 collaboration strategies and benchmarks demonstrating average outperformance over single models in 61 percent of (model, data) pairs.
citing papers explorer
-
Decomposing how prompting steers behavior
A geometric decomposition framework shows that affine transformations best recover prompt-induced task geometry and behavior in language and vision models across multiple datasets.
-
When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search
Prompt-boundary directional alignment enables geometry-guided search that cuts trials to 95% best utility by 39.8% on average, while concept granularity predicts remaining difficulty via directional heterogeneity.
-
Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs
Memory Inception is a training-free method that injects latent KV banks at chosen layers to steer LLMs, achieving superior control-drift balance and up to 118x storage reduction on personality and structured-reasoning tasks.
-
MoCo: A One-Stop Shop for Model Collaboration Research
MoCo supplies a unified library of 26 collaboration strategies and benchmarks demonstrating average outperformance over single models in 61 percent of (model, data) pairs.