Using In-Context Learning to Improve Dialogue Safety
While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating toxic content, which often perpetuates social biases or stereotypes. We investigate a retrieval-based method for reducing bias and toxicity in responses from chatbots. It uses in-context learning to steer a model towards safer generations. Concretely, to generate a response to an unsafe dialogue context, we retrieve demonstrations of safe responses to similar dialogue contexts. We find our method performs competitively with strong baselines without requiring training. For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4.04% more than our approach. Finally, we also propose a re-ranking procedure which can further improve response safeness.
Code (0)
등록된 구현이 없습니다.
Tasks
In-Context LearningRe-RankingRetrievalSimilar Papers 제목 키워드 기반
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corre…
On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark
Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corre…
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification. While large language models (LLMs) have shown promise in autom…
MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
Multimodal large language models (MLLMs) are increasingly deployed as assistants that interact through text and images, making it crucial to evaluate contextual safety when risk depends on both the visual scene and the e…
Intent RecognitionSteering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Large language models (LLMs) are highly vulnerable to jailbreaking attacks, wherein adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detect…
Safety Alignment