Controllable Affective Generation via Latent Vector Steering
cs.CL, cs.AI
Submitted: 2026-08-26
Updated: 2026-08-26
Code: https://github.com/chicosirius/EmoVec
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A General Language Assistant as a Laboratory for Alignment
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Localizing Persona Representations in LLMs
- Social Chemistry 101: Learning to Reason about Social and Moral Norms
- Training language models to be warm and empathetic makes them less reliable and more sycophantic
- Probing then Editing Response Personality of Large Language Models
- Understanding the Effects of RLHF on LLM Generalisation and Diversity
- Large Language Models Understand and Can be Enhanced by Emotional Stimuli
- G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
- The Linear Representation Hypothesis and the Geometry of Large Language Models
- SocialIQA: Commonsense Reasoning about Social Interactions
- Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
- CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling
- R2MED: A Benchmark for Reasoning-Driven Medical Retrieval
- Steering Language Models With Activation Engineering
- Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities
- Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective
- NormBank: A Knowledge Bank of Situational Social Norms
- Representation Engineering: A Top-Down Approach to AI Transparency
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