cd /news/large-language-models/low-agreeableness-persona-conditioni… · home topics large-language-models article
[ARTICLE · art-42915] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning

Researchers at arXiv introduced a persona-driven rewriting pipeline that conditions user turns on low agreeableness to reduce jailbreak susceptibility and harmful output rates in LLMs fine-tuned for social warmth, preserving conversational warmth without safety labels or training objective changes.

read1 min views1 publishedJun 29, 2026

arXiv:2606.27709v1 Announce Type: new Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We investigate a related but distinct failure mode: warmth fine-tuning also weakens adversarial safety, making models more susceptible to jailbreaks and harmful output generation. We examine whether this reflects an inherent consequence of empathetic adaptation or an artifact of data construction. To address this, we introduce a persona-driven rewriting pipeline that conditions user turns on low agreeableness and pairs this with warm, de-escalating assistant responses. Across three experiments on four models, our approach reduces jailbreak susceptibility and harmful output rates relative to generic warmth fine-tuning baselines, while preserving conversational warmth. Representational probing provides suggestive evidence that this conditioning reduces the geometric alignment between warmth and compliance directions in latent space. These results show that safer empathetic fine-tuning is achievable through data design alone, without safety labels, harm detectors, or changes to the training objective.

── more in #large-language-models 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/low-agreeableness-pe…] indexed:0 read:1min 2026-06-29 ·