Lifeng Shang

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4 ACL 2026 MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers ACL 2026 EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing AAAI 2026 ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool learning AAAI 2026 Process Evaluation for Agentic Systems EACL 2026 Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning ACL 2026 How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study ACL 2026 ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis NAACL 2025 Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape ICML 2025 ToolACE: Winning the Points of LLM Function Calling ICLR 2025 Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization ICLR 2025 RevisEval: Improving LLM-as-a-Judge via Response-Adapted References ICLR 2025 Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge ACL 2025 Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning ACL 2025 Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification ACL 2025 Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing ACL 2025 Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction ACL 2025 Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework ACL 2025 Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step NAACL 2025 More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression EMNLP 2025 Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning EMNLP 2025 Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios ACL 2024 MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models EMNLP 2024 Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis ICLR 2024 Visually Guided Generative Text-Layout Pre-training for Document Intelligence NAACL 2024 Preparing Lessons for Progressive Training on Language Models AAAI 2024 Does the Generator Mind Its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer COLING 2024 FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models ACL 2024 Learning to Edit: Aligning LLMs with Knowledge Editing ACL 2024 ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models ACL 2024 M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models ACL 2024 Retrieval-based Disentangled Representation Learning with Natural Language Supervision ICLR 2024 Prompt-Based Length Controlled Generation with Multiple Control Types ACL 2024 Gradually Excavating External Knowledge for Implicit Complex Question Answering EMNLP 2023 Reusing Pretrained Models by Multi-linear Operators for Efficient Training NIPS 2023 Self-Supervised Logic Induction for Explainable Fuzzy Temporal Commonsense Reasoning AAAI 2023 Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models ACL 2023 mCLIP: Multilingual CLIP via Cross-lingual Transfer ACL 2023 AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models ACL 2023 NewsDialogues: Towards Proactive News Grounded Conversation ACL 2023 Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment EMNLP 2023 Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation EMNLP 2022 Exploring extreme parameter compression for pre-trained language models ICLR 2022 Read before Generate! Faithful Long Form Question Answering with Machine Reading ACL 2022 MINER: Multi-Interest Matching Network for News Recommendation ACL 2022 Controlled Text Generation Using Dictionary Prior in Variational Autoencoders ACL 2022 Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering ACL 2022 Compression of Generative Pre-trained Language Models via Quantization ACL 2022 Towards Efficient Post-training Quantization of Pre-trained Language Models NIPS 2022 bert2BERT: Towards Reusable Pretrained Language Models ACL 2022 G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks EMNLP 2022 MTRec: Multi-Task Learning over BERT for News Recommendation ACL 2022 Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation ACL 2022 How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis ACL 2022 LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling EMNLP 2022 Pre-training Language Models with Deterministic Factual Knowledge EMNLP 2022 Improving Unsupervised Question Answering via Summarization-Informed Question Generation EMNLP 2021 GhostBERT: Generate More Features with Cheap Operations for BERT IJCNLP 2021 GhostBERT: Generate More Features with Cheap Operations for BERT ACL 2021 AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models ACL 2021 BinaryBERT: Pushing the Limit of BERT Quantization ACL 2021 Generate & Rank: A Multi-task Framework for Math Word Problems EMNLP 2021 DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling EMNLP 2021 Noninvasive Self-attention for Side Information Fusion in Sequential Recommendation AAAI 2021 Reweighting Augmented Samples by Minimizing the Maximal Expected Loss ICLR 2021 On Position Embeddings in BERT ICLR 2021 Improved OOD Generalization via Adversarial Training and Pretraing ICML 2021 HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions AAAI 2021 A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering ACL 2021 A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering IJCNLP 2021 BinaryBERT: Pushing the Limit of BERT Quantization IJCNLP 2021 AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models IJCNLP 2021 DynaBERT: Dynamic BERT with Adaptive Width and Depth NIPS 2020 TinyBERT: Distilling BERT for Natural Language Understanding EMNLP 2020 TernaryBERT: Distillation-aware Ultra-low Bit BERT EMNLP 2020 An Investigation of Few-Shot Learning in Spoken Term Classification INTERSPEECH 2020 Dialog State Tracking with Reinforced Data Augmentation AAAI 2020 Decomposable Neural Paraphrase Generation ACL 2019 Paraphrase Generation with Deep Reinforcement Learning EMNLP 2018 Neural Generative Question Answering IJCAI 2016 Neural Responding Machine for Short-Text Conversation ACL 2015 Multimodal Convolutional Neural Networks for Matching Image and Sentence ICCV 2015 Neural Responding Machine for Short-Text Conversation IJCNLP 2015