| @misc{turner2023actadd, |
| author = {Alex Turner and Lisa Thiergart and David Udell and Gavin Leech and Ulisse Mini and Monte MacDiarmid}, |
| title = {{Activation Addition: Steering Language Models Without Optimization}}, |
| year = {2023}, |
| eprint = {2308.10248v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2308.10248v1}, |
| note = {Cited version dated 2023-08-20; metadata checked 2026-11-13} |
| } |
| |
| @misc{panickssery2024caa, |
| author = {Nina Panickssery and Nick Gabrieli and Julian Schulz and Meg Tong and Evan Hubinger and Alexander Matt Turner}, |
| title = {{Steering Llama 2 via Contrastive Activation Addition}}, |
| year = {2024}, |
| eprint = {2312.06681v4}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2312.06681v4}, |
| note = {Cited version dated 2024-07-05; metadata checked 2026-11-13} |
| } |
| |
| @misc{wu2025emotion, |
| author = {Xiuwen Wu and Hao Wang and Zhiang Yan and Xiaohan Tang and Pengfei Xu and Wai-Ting Siok and Ping Li and Jia-Hong Gao and Bingjiang Lyu and Lang Qin}, |
| title = {{AI shares emotion with humans across languages and cultures}}, |
| year = {2025}, |
| eprint = {2506.13978v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2506.13978v1}, |
| note = {Cited version dated 2025-06-11; metadata checked 2026-11-13} |
| } |
| |
| @misc{diallo2026style, |
| author = {Diaoulé Diallo and Katharina Dworatzyk and Sophie Jentzsch and Peer Schütt and Sabine Theis and Tobias Hecking}, |
| title = {{The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation}}, |
| year = {2026}, |
| eprint = {2601.21505v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2601.21505v1}, |
| note = {Cited version dated 2026-01-29; metadata checked 2026-11-13} |
| } |
| |
| @misc{sun2026emotion, |
| author = {Moran Sun and Tianlin Li and Yuwei Zheng and Zhenhong Zhou and Aishan Liu and Xianglong Liu and Yang Liu}, |
| title = {{How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study}}, |
| year = {2026}, |
| eprint = {2604.00005v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2604.00005v1}, |
| note = {Cited version dated 2026-03-09; metadata checked 2026-11-13} |
| } |
| |
| @misc{jeong2026emotion, |
| author = {Jihoon Jeong}, |
| title = {{Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison}}, |
| year = {2026}, |
| eprint = {2604.04064v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2604.04064v1}, |
| note = {Cited version dated 2026-04-05; metadata checked 2026-11-13} |
| } |
| |
| @misc{shu2026emotion, |
| author = {Bangzhao Shu and Arinjay Singh and Mai ElSherief}, |
| title = {{Why Are Some Emotions Harder for LLMs? Uncovering the Causal Mechanisms of Emotion Inference via Sparse Autoencoders}}, |
| year = {2026}, |
| eprint = {2604.25866v3}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2604.25866v3}, |
| note = {Cited version dated 2026-10-24; metadata checked 2026-11-13} |
| } |
| |
| @misc{wang2026readbest, |
| author = {Yibo Wang and Jisheng Dang and Bimei Wang and Yitao Wu and Wencan Zhang and Hong Peng and Jizhao Liu and Bin Hu and Qi Tian and Tat-Seng Chua}, |
| title = {{Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models}}, |
| year = {2026}, |
| eprint = {2609.22135v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2609.22135v1}, |
| note = {Cited version dated 2026-08-24; metadata checked 2026-11-13} |
| } |
| |
| @misc{ha2026empathy, |
| author = {JuHeon Ha and Byounghan Lee and Yunseo Choi and Kyung-Ah Sohn}, |
| title = {{Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMs}}, |
| year = {2026}, |
| eprint = {2609.15654v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2609.15654v1}, |
| note = {Cited version dated 2026-09-14; metadata checked 2026-11-13} |
| } |
| |
| @misc{cui2025pas, |
| author = {Sasha Cui and Zhongren Chen}, |
| title = {{Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models}}, |
| year = {2025}, |
| eprint = {2509.22739v3}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2509.22739v3}, |
| note = {Cited version dated 2026-05-15; metadata checked 2026-11-13} |
| } |
| |
| @misc{ferrando2025dsas, |
| author = {Alex Ferrando and Xavier Suau and Jordi Gonzàlez and Pau Rodriguez}, |
| title = {{Dynamically Scaled Activation Steering}}, |
| year = {2025}, |
| eprint = {2512.03661v2}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2512.03661v2}, |
| note = {Cited version dated 2026-07-30; metadata checked 2026-11-13} |
| } |
| |
| @misc{yang2026steerscope, |
| author = {Haotian Yang and Huikang Jiang and Yucheng Wu and Wen-Jie Jiang and Chenpeng Wang and Yibin Lou and Liangming Pan}, |
| title = {{Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods}}, |
| year = {2026}, |
| eprint = {2610.07722v1}, |
| archivePrefix = {arXiv}, |
| url = {https://arxiv.org/abs/2610.07722v1}, |
| note = {Cited version dated 2026-10-06; metadata checked 2026-11-13} |
| } |
| |
| |
