Selected Publications
Full list see my Google Scholar
* Corresponding author
2026
2025
-
- A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank CloneNeurIPS, 2025
- Iterative self-incentivization empowers large language models as agentic searchersNeurIPS, 2025
-
-
- Improving sequential recommenders through counterfactual augmentation of system exposureSIGIR, 2025
-
- Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent SystemsEMNLP, 2025
-
- Model Meets Knowledge: Analyzing Knowledge Types for Conversational Recommender SystemsRecSys, 2025
-
- Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language ModelsFindings of ACL, 2025
- Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model GeneralizationFindings of ACL, 2025
- Tool learning in the wild: Empowering language models as automatic tool agentsThe Web Conference, 2025
- A cooperative multi-agent framework for zero-shot named entity recognitionThe Web Conference, 2025
-
- ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative RetrievalUnder review, 2025
-
2024
-
-
-
-
-
-
-
- Generate-then-ground in retrieval-augmented generation for multi-hop question answeringACL, 2024
-
- CAUSE: Counterfactual assessment of user satisfaction estimation in task-oriented dialogue systemsFindings of ACL, 2024
-
- Generative retrieval as multi-vector dense retrieval,
(Best Full Paper Runner Up Award)SIGIR, 2024 -
-
-
- Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure,
(Best Full Paper Runner Up Award)WSDM, 2024 -
-
- Confucius: Iterative tool learning from introspection feedback by easy-to-difficult curriculumAAAI, 2024
-
2023
-
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agent,
(Outstanding Paper Award)EMNLP, 2023 -
- Generalizing Few-Shot Named Entity Recognizers to Unseen Domains with Type-Related FeaturesEMNLP, 2023
-
-
-
-
- Multi-Source Multi-Type Knowledge Exploration and Exploitation for Dialogue GenerationEMNLP, 2023
- Iteratively Learning Representations for Unseen Entities with Inter-Rule CorrelationsCIKM, 2023
-
-
-
-
-
- Contrastive State Augmentations for Reinforcement Learning-Based Recommender Systems.SIGIR, 2023
-
-
-
- Variational Reasoning over Incomplete Knowledge Graphs for Conversational Recommendation.WSDM, 2023
2022
2021
2020
2019
2018
-
- Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures.ACL, 2018
-
-
-
- A Path-constrained Framework for Discriminating Substitutable and Complementary Products in E-commerce.
(Best Student Paper Award)WSDM, 2018