Paper

Small edits, large models: How Wikipedia advocacy shapes LLM values

Unreadunread

AI summary

arXiv:2606. 24890v1 Announce Type: new Abstract: Can a small group of volunteers shape how AI systems discuss animal welfare, just by editing Wikipedia?

Reading status

Priority

About this paper

Authors: Jasmine Brazilek, Maria Navas, Alexa Gnauck
Released: 2026-06-25 (14d ago)
Topic: Related to current project
Relation to my work: Read next because Small edits, large models: How Wikipedia advocacy shapes LLM values 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: text, eval, source, rate, control, trained, language, model. Source: arxiv cs.CL (NLP).
arXiv: 2606.24890

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Small edits, large models: How Wikipedia advocacy shapes LLM values. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.