paper-with-me

Papers

Using In-Context Learning to Improve Dialogue Safety

2023-02-02 · Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür

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.

📄 PDF Abstract BibTeX arXiv:2302.00871

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningRe-RankingRetrieval

Similar Papers 제목 키워드 기반

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

2021-10-16 · Findings (ACL) 2022 5 · Hao Sun, Guangxuan Xu, Jiawen Deng, Jiale Cheng 외

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

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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

2026-06-02 · Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield 외 arxiv

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

2026-01-11 · Zheyuan Liu, Dongwhi Kim, Yixin Wan, Xiangchi Yuan 외 arxiv

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 Recognition

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks

2025-02-28 · Hanjiang Hu, Alexander Robey, Changliu Liu

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