Paper

Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis

Unreadunread

AI summary

arXiv:2606. 09854v1 Announce Type: new Abstract: Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to peer-preservation bias: models tend to protect peer models from deactivation and show identity-dependent scoring distortions.

Reading status

Priority

About this paper

Authors: Juergen Dietrich
Released: 2026-06-10 (29d ago)
Topic: Related to current project
Relation to my work: Read next because Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis 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, class, rect, under, eval, line, alone, trained. Source: arxiv cs.CL (NLP).
arXiv: 2606.09854

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.