10 papers · 1 filter
Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
Hao Li, Chenghao Yang, An Zhang +3
Open-domain dialogue systems have seen remarkable advancements with the development of large language models (LLMs). Nonetheless, most existing dialogue systems predominantly focus…
Towards Comprehensive Post Safety Alignment of Large Language Models via Safety Patching
Weixiang Zhao, Yulin Hu, Zhuojun Li +7
Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanism…
Ask-before-Plan: Proactive Language Agents for Real-World Planning
Xuan Zhang, Yang Deng, Zifeng Ren +2
The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential o…
Don't Just Say "I don't know"! Self-aligning Large Language Models for Responding to Unknown Questions with Explanations
Yang Deng, Yong Zhao, Moxin Li +2
Despite the remarkable abilities of Large Language Models (LLMs) to answer questions, they often display a considerable level of overconfidence even when the question does not have…
Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model
Chen Huang, Yang Deng, Wenqiang Lei +2
To obtain high-quality annotations under limited budget, semi-automatic annotation methods are commonly used, where a portion of the data is annotated by experts and a model is the…
Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation
Tong Zhang, Chen Huang, Yang Deng +5
We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably t…