Before You Continue: Evaluating Time-Sensitive Safety Awareness in Conversational Assistants
cs.CL
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/peidid/TASC_release
Terminology
Sources
- HealthBench: Evaluating Large Language Models Towards Improved Human Health
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Can LLMs Perceive Time? An Empirical Investigation
- ProactBench: Beyond What The User Asked For
- Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time
- GPT-4o System Card
- From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents
- Can I Take Another Dose? DoseBench: Evaluating LLM Decision-Making in OTC Dosing QA
- Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
- Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues
- MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs
- OpenAI GPT-5 System Card
- Kimi K3: Open Frontier Intelligence
- Measuring Iterative Temporal Reasoning with Time Puzzles
- Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents
- TriggerBench: Investigating Prospective Memory for Large Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data