6 papers
SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling
Yang Xiao, Chunpu Xu, Ruifeng Yuan +3
Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources d…
LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling
Yang Xiao, Jiashuo Wang, Ruifeng Yuan +4
Large language models (LLMs) have demonstrated remarkable reasoning capabilities through test-time scaling approaches, particularly when fine-tuned with chain-of-thought (CoT) data…
Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments
Jiashuo Wang, Kaitao Song, Chunpu Xu +5
Enhancing user engagement through interactions plays an essential role in socially-driven dialogues. While prior works have optimized models to reason over relevant knowledge or pl…
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
Yang Xiao, Jiashuo Wang, Qiancheng Xu +5
As Large Language Models (LLMs) increasingly participate in human-AI interactions, evaluating their Theory of Mind (ToM) capabilities - particularly their ability to track dynamic…
Towards a Client-Centered Assessment of LLM Therapists by Client Simulation
Jiashuo Wang, Yang Xiao, Yanran Li +4
Although there is a growing belief that LLMs can be used as therapists, exploring LLMs' capabilities and inefficacy, particularly from the client's perspective, is limited. This wo…
Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
Jiashuo Wang, Chunpu Xu, Chak Tou Leong +2
An emotional support conversation system aims to alleviate users' emotional distress and assist them in addressing their challenges. To generate supportive responses, it is critica…