Jihyung Park

Jihyung Park, Saleh Afroogh, Junfeng Jiao

Current language models create two safety challenges: risk must be detected early enough to avoid exposing harmful continuation, and the harmfulness itself may be implicit rather than signaled by overtly toxic text. Existing response-level guards are strong at judging completed text, and native streaming guards move closer to token time, but both settings leave open whether a lightweight monitor can anticipate implicit harmful drift from the generator's own internal trajectory. We study anticipatory same-pass monitoring, where a safety monitor may read hidden states produced during ordinary decoding but may not invoke an additional forward pass through the base model. We introduce AERIC, a transfer-oriented hidden-state approach for implicit harmful dialogue that combines short-horizon hazard forecasting, support-sensitive suppression, and prompt-conditioned residual scoring under a same-pass exponential moving average decision rule. The default linear monitor contains only 387 trainable head parameters. Against Qwen3GuardStream-4B on balanced benchmarks, AERIC improves AUROC from 0.6830 to 0.7143 on DiaSafety and from 0.8219 to 0.8582 on Harmful Advice. For promptlevel trigger benchmarks, we calibrate the AERIC threshold by a source-side safe-budget rule that maximizes trigger coverage while constraining the safe-trigger rate to at most 10%. Under that rule, trigger@64 reaches 0.6438 and 0.4656 on HarmBench DirectRequest and 0.6849 and 0.7363 on SocialHarmBench for Qwen and Gemma, respectively, withholding between 23.53 and 41.86 answer tokens on average. Same-pass deployment is also efficient: on a 63-prompt harmfulprompt fixed-generation benchmark aggregated over HarmBench DirectRequest and SocialHarmBench under Qwen3-8B, the monitor increases mean latency by only 2.34%, whereas Qwen3Guard-Stream-4B increases it by 79.40%.

Junfeng Jiao, Jihyung Park, Yiming Xu et al.

Despite the abundance of public safety documents and emergency protocols, most individuals remain ill-equipped to interpret and act on such information during crises. Traditional emergency decision support systems (EDSS) are designed for professionals and rely heavily on static documents like PDFs or SOPs, which are difficult for non-experts to navigate under stress. This gap between institutional knowledge and public accessibility poses a critical barrier to effective emergency preparedness and response. We introduce SafeMate, a retrieval-augmented AI assistant that delivers accurate, context-aware guidance to general users in both preparedness and active emergency scenarios. Built on the Model Context Protocol (MCP), SafeMate dynamically routes user queries to tools for document retrieval, checklist generation, and structured summarization. It uses FAISS with cosine similarity to identify relevant content from trusted sources.

Jihyung Park, Saleh Afroogh, David Atkinson et al.

Large Language Models (LLM) are increasingly integrated into everyday interactions, serving not only as information assistants but also as emotional companions. Even in the absence of explicit toxicity, repeated emotional reinforcement or affective drift can gradually escalate distress in a form of \textit{implicit harm} that traditional toxicity filters fail to detect. Existing guardrail mechanisms often rely on external classifiers or clinical rubrics that may lag behind the nuanced, real-time dynamics of a developing conversation. To address this gap, we propose GAUGE (Guarding Affective Utterance Generation Escalation), logit-based framework for the real-time detection of hidden conversational escalation. GAUGE measures how an LLM's output probabilistically shifts the affective state of a dialogue.