PulseAugur
EN
LIVE 02:29:48

LLMs Refusal Strategies Explored: PsychoSafe Improves Support, Evasion Attacks Undermine Safety

By PulseAugur Editorial · [3 sources] ·

Researchers have developed PsychoSafe, a framework to improve how large language models refuse harmful requests by employing psychologically informed communication strategies. This approach reframes refusals as supportive interactions, enhancing external resource referral and psychological grounding. Separately, another study introduces Latent-space Attacks for Refusal Evasion, which analyzes how to bypass LLM safety mechanisms by manipulating internal model representations to suppress refusal behavior. AI

IMPACT Developments in LLM refusal strategies and evasion techniques highlight ongoing challenges in AI safety and alignment.

RANK_REASON Two research papers on LLM safety and refusal mechanisms.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

LLMs Refusal Strategies Explored: PsychoSafe Improves Support, Evasion Attacks Undermine Safety

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Two research papers on LLM safety and refusal mechanisms.
Source corroboration
3 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
safety, paper
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
93 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

Full methodology in our editorial standards.

COVERAGE [3]

  1. arXiv cs.CL TIER_1 English(EN) · Anne Lauscher ·

    PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

    Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpful. In high-risk interactions involving crisis, coercion, or escalating intent, blunt non-compliance…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

    A psychologically-informed refusal framework called PsychoSafe is developed for large language models to improve harmful request handling through structured supportive communication, showing enhanced refusal quality and resource referral while maintaining performance on non-refus…

  3. arXiv cs.AI TIER_1 English(EN) · Giorgio Piras, Raffaele Mura, Fabio Brau, Maura Pintor, Luca Oneto, Fabio Roli, Battista Biggio ·

    Latent-space Attacks for Refusal Evasion in Language Models

    arXiv:2605.21706v2 Announce Type: replace Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by ablating a refusal direction from model activati…

RELATED ENTITIES

RELATED TOPICS