5 papers
Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
Sophia Xiao Pu, Yumo Xu, Sailik Sengupta +5
Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retaining it whole or discarding it…
MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarization
Yinhong Liu, Jianfeng He, Hang Su +6
Multimodal Dialogue Summarization (MDS) is a critical task with wide-ranging applications. To support the development of effective MDS models, robust automatic evaluation methods a…
Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
Binwei Yao, Chao Shang, Wanyu Du +6
Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS)…
Learning Label Hierarchy with Supervised Contrastive Learning
Ruixue Lian, William A. Sethares, Junjie Hu
Supervised contrastive learning (SCL) frameworks treat each class as independent and thus consider all classes to be equally important. This neglects the common scenario in which l…
Incremental user embedding modeling for personalized text classification
Ruixue Lian, Che-Wei Huang, Yuqing Tang +3
Individual user profiles and interaction histories play a significant role in providing customized experiences in real-world applications such as chatbots, social media, retail, an…