Paper

EUDAIMONIA: Evaluating Undesirable Dynamics in AI

Unreadunread

AI summary

arXiv:2605. 30654v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as conversational partners for companionship, emotional disclosure, and interpersonal advice, but the social dynamics of these interactions can create harms that are not captured by capability-oriented or traditional safety evaluations.

Reading status

Priority

About this paper

Authors: Jun Rui Huang, Wang Bill Zhu, Ziyi Liu, Nathanael Fast, Ravi Iyer, Robin Jia
Released: 2026-06-01 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because EUDAIMONIA: Evaluating Undesirable Dynamics in AI overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, strong, persona, alignment, eval, rate, control, alone. Source: arxiv cs.CL (NLP).
arXiv: 2605.30654

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to EUDAIMONIA: Evaluating Undesirable Dynamics in AI. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.