works on
llm safety 2causal temporal modeling 1hallucination detection 1multi-agent systems 1multi-turn dialogue 1pre-hoc risk inference 1risk forecasting 1risk propagation 1trajectory-level prediction 1

From the 2 of 2 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions

Shi Lin, Peng Qian, Dinghao Liu +5

The paper introduces Recast, a framework that predicts safety risks in multi‑turn interactions with large language models by forecasting how risks evolve over dialogue trajectories…