Publications by Conference

AAAI

• 2021-01 » Enhancing Scientific Papers Summarization with Citation Graph (AAAI 2021)

ACL

• 2020-01 » Extractive Summarization as Text Matching (ACL 2020)
• 2020-01 » Heterogeneous Graph Neural Networks for Extractive Document Summarization (ACL 2020)
• 2019-01 » Searching for Effective Neural Extractive Summarization: What Works and What's Next (ACL 2019)

ACL Findings

• 2021-01 » Contrastive Aligned Joint Learning for Multilingual Summarization (ACL Findings 2021)

CoLM

• 2026-04 » Learning to Interrupt in Language-based Multi-agent Communication (CoLM 2026)

EMNLP

• 2024-01 » Learning Personalized Alignment for Evaluating Open-ended Text Generation (EMNLP 2024)
• 2023-01 » InstructScore: Towards Explainable Text Generation Evaluation with Automatic Feedback (EMNLP 2023)
• 2023-01 » Learning from Mistakes via Cooperative Study Assistant for Large Language Models (EMNLP 2023)

EMNLP Findings

• 2020-01 » CDEvalSumm: An Empirical Study of Cross-dataset Evaluation for Neural Summarization Systems (EMNLP Findings 2020)

ICLR

• 2026-01 » Strategic Planning and Rationalizing on Trees Make LLMs Better Debaters (ICLR 2026)
• 2025-01 » TypedThinker: Typed Thinking Improves Large Language Model Reasoning (ICLR 2025)
• 2023-01 » On Pre-training Language Model for Antibody (ICLR 2023)

ICML

• 2026-01 » Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks (ICML 2026)

KDD

• 2024-01 » Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learning (KDD 2024)
• 2023-01 » Accelerating Antimicrobial Peptide Discovery with Latent Structure (KDD 2023)

NAACL

• 2025-01 » Scaling LLM Inference with Optimized Sample Compute Allocation (NAACL 2025)

NAACL Findings

• 2022-01 » MTG: A Benchmark Suite for Multilingual Text Generation (NAACL Findings 2022)

NLPCC

• 2021-01 » CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level (NLPCC 2021)

Nature Communications

• 2025-01 » DNALongBench: A Benchmark Suite for Long-Range DNA Prediction Tasks (Nature Communications 2025)

NeurIPS

• 2023-01 » ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers (NeurIPS 2023)

Preprint

• 2025-01 » RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems (arXiv 2025)
• 2024-01 » Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models (arXiv 2024)
• 2019-01 » Exploring Domain Shift in Extractive Text Summarization (arXiv 2019)

Under Review

• 2026-06 » CRAB-Bench: Evaluating LLM Agents under Complex Task Dependencies and Human-aligned User Simulation