Dayiheng Liu

Controllable LLM Reasoning via Sparse Autoencoder-Based Steering ACL 2026 PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice ACL 2026 MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation ACL 2026 HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning ACL 2025 P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs EMNLP 2025 DataMan: Data Manager for Pre-training Large Language Models ICLR 2025 START: Self-taught Reasoner with Tools EMNLP 2025 ProcessBench: Identifying Process Errors in Mathematical Reasoning ACL 2025 NOVA-63: Native Omni-lingual Versatile Assessments of 63 Disciplines EMNLP 2025 Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models ACL 2025 LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback ACL 2025 The Lessons of Developing Process Reward Models in Mathematical Reasoning ACL 2025 Talk Funny! A Large-Scale Humor Response Dataset with Chain-of-Humor Interpretation AAAI 2024 MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation COLING 2024 Knowledge Enhanced Pre-training for Cross-lingual Dense Retrieval COLING 2024 How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition ACL 2024 Rationales for Answers to Simple Math Word Problems Confuse Large Language Models ACL 2024 Bridging the Domain Gaps in Context Representations for k-Nearest Neighbor Neural Machine Translation ACL 2023 MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization EMNLP 2023 Noisy Pair Corrector for Dense Retrieval EMNLP 2023 Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation EMNLP 2023 EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning NIPS 2023 Dynamic Voting for Efficient Reasoning in Large Language Models EMNLP 2023 Tailor: A Soft-Prompt-Based Approach to Attribute-Based Controlled Text Generation ACL 2023 Fantastic Expressions and Where to Find Them: Chinese Simile Generation with Multiple Constraints ACL 2023 Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis NAACL 2022 KGR4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation AAAI 2022 Frequency-Aware Contrastive Learning for Neural Machine Translation AAAI 2022 UniTE: Unified Translation Evaluation ACL 2022 Unsupervised Preference-Aware Language Identification ACL 2022 Attention Mechanism with Energy-Friendly Operations ACL 2022 GCPG: A General Framework for Controllable Paraphrase Generation ACL 2022 Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? EMNLP 2022 Alibaba-Translate China’s Submission for WMT2022 Metrics Shared Task EMNLP 2022 Alibaba-Translate China’s Submission for WMT 2022 Quality Estimation Shared Task EMNLP 2022 Self-supervised Product Title Rewrite for Product Listing Ads NAACL 2022 Dangling-Aware Entity Alignment with Mixed High-Order Proximities NAACL 2022 Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation NAACL 2022 GLGE: A New General Language Generation Evaluation Benchmark ACL 2021 RoBLEURT Submission for WMT2021 Metrics Task EMNLP 2021 Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation ACL 2021 POS-Constrained Parallel Decoding for Non-autoregressive Generation ACL 2021 BANG: Bridging Autoregressive and Non-autoregressive Generation with Large Scale Pretraining ICML 2021 Towards User-Driven Neural Machine Translation IJCNLP 2021 POS-Constrained Parallel Decoding for Non-autoregressive Generation IJCNLP 2021 Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation IJCNLP 2021 GLGE: A New General Language Generation Evaluation Benchmark IJCNLP 2021 Mask Attention Networks: Rethinking and Strengthen Transformer NAACL 2021 Towards User-Driven Neural Machine Translation ACL 2021 Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation EMNLP 2020 RikiNet: Reading Wikipedia Pages for Natural Question Answering ACL 2020 Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning AAAI 2020 Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space EMNLP 2020 ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training EMNLP 2020 TIGS: An Inference Algorithm for Text Infilling with Gradient Search ACL 2019