Cross-Prompt Reuse of Entity-Replacement Responses
cs.CL, cs.AI
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/lm-pub-quiz/BEAR
Terminology
Sources
- Relation Before Entity: Deferred Commitment in Language Model Factual Recall
- "I May Not Have Articulated Myself Clearly": Diagnosing Dynamic Instability in LLM Reasoning at Inference Time
- Decomposing how prompting steers behavior
- Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
- Gemma 2: Improving Open Language Models at a Practical Size
- Addressing divergent representations from causal interventions on neural networks
- The Llama 3 Herd of Models
- How to use and interpret activation patching
- Inspecting and Editing Knowledge Representations in Language Models
- Improving Activation Steering in Language Models with Mean-Centring
- Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
- Steering Interference Reflects the Model's Defaults, Not the Behavior Directions
- A Refined Analysis of Massive Activations in LLMs
- Qwen2.5 Technical Report
- Steering Language Models With Activation Engineering
- Functional Abstraction of Knowledge Recall in Large Language Models
- Representation Engineering: A Top-Down Approach to AI Transparency
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