2 papers
cs.HC2026
Where the Evidence Lives: Auditing AI Companions' Self-Descriptions
Seiya Ikeda, Shin-nosuke Ishikawa
Companion agents describe themselves: they remember, they understand their users, the relationship has changed them. We argue that such accounts, and the experience ratings that se…
cs.AI2026
When AI Says It Feels
Shin-nosuke Ishikawa, Seiya Ikeda, Hirotsugu Ohba
Large language models (LLMs) are generally constrained from expressing feelings through human-preference alignment in post-training processes. This policy is designed using a top-d…