2025
RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
Jerry Huang, Siddarth Madala, Risham Sidhu, Cheng Niu, Hao Peng, Julia Hockenmaier, Tong Zhang
EACL 2026 Findings
We introduce RAG-RL, an answer generation model trained to identify and reason over larger sets of retrieved information using reinforcement learning and curriculum learning.
RAG-RL: Advancing Retrieval-Augmented Generation via RL and Curriculum Learning
Jerry Huang, Siddarth Madala, Risham Sidhu, Cheng Niu, Hao Peng, Julia Hockenmaier, Tong Zhang
EACL 2026 Findings
We introduce RAG-RL, an answer generation model trained to identify and reason over larger sets of retrieved information using reinforcement learning and curriculum learning.
Contextual Relevance: Modeling Context-Conditioned Relevance for Improving Document Reranking
Jerry Huang, Siddarth Madala, Cheng Niu, Julia Hockenmaier, Tong Zhang
ACL 2026 Main Conference.
We investigate the context-dependent nature of LLM-based relevance judgements in the document reranking setting.
Contextual Relevance: Modeling Context-Conditioned Relevance for Improving Document Reranking
Jerry Huang, Siddarth Madala, Cheng Niu, Julia Hockenmaier, Tong Zhang
ACL 2026 Main Conference.
We investigate the context-dependent nature of LLM-based relevance judgements in the document reranking setting.
GUIDE: Towards Scalable Advising for Research Ideas
Yaowenqi Liu, BingXu Meng, Rui Pan, Jerry Huang, Tong Zhang
ACL 2026 Main Conference.
We introduce a scalable advising system for research idea evaluation by leveraging a compressed literature database and fine-tuning techniques.
GUIDE: Towards Scalable Advising for Research Ideas
Yaowenqi Liu, BingXu Meng, Rui Pan, Jerry Huang, Tong Zhang
ACL 2026 Main Conference.
We introduce a scalable advising system for research idea evaluation by leveraging a compressed literature database and fine-tuning techniques.