6 papers
Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces
Congchao Wang, Diwakar Singh, Qiaozi Gao +3
Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during reinforcement lear…
Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
Yaopei Zeng, Congchao Wang, JianHang Chen +3
LLM agents act in external environments where each action changes the state that later decisions condition on, and where a single wrong step can waste interaction budget or trigger…
ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
Yaopei Zeng, Congchao Wang, Blake JianHang Chen +1
Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive lar…
Gatekeeper: Improving Model Cascades Through Confidence Tuning
Stephan Rabanser, Nathalie Rauschmayr, Achin Kulshrestha +5
Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these chal…
Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning
Kai Zhang, Congchao Wang, Liqian Peng +2
Large Language Models (LLMs) have gained significant attention in on-device applications due to their remarkable performance across real-world tasks. However, on-device LLMs often…
Cascade-Aware Training of Language Models
Congchao Wang, Sean Augenstein, Keith Rush +5
Reducing serving cost and latency is a fundamental concern for the deployment of language models (LMs) in business applications. To address this, cascades of LMs offer an effective…