Yasheng Wang

ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool learning AAAI 2026 EssayBench: Evaluating Large Language Models in Multi-Genre Chinese Essay Writing AAAI 2026 Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation ACL 2025 Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance ICLR 2025 NILE: Internal Consistency Alignment in Large Language Models EMNLP 2025 Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization ICLR 2025 RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation EMNLP 2025 NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging EMNLP 2025 ToolACE: Winning the Points of LLM Function Calling ICLR 2025 Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step NAACL 2025 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 Learning Evolving Tools for Large Language Models ICLR 2025 SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION ICLR 2025 RevisEval: Improving LLM-as-a-Judge via Response-Adapted References ICLR 2025 Humanity’s Last Code Exam: Can Advanced LLMs Conquer Human’s Hardest Code Competition? EMNLP 2025 Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning EMNLP 2025 Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge ACL 2025 DebateCoder: Towards Collective Intelligence of LLMs via Test Case Driven LLM Debate for Code Generation ACL 2025 Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification ACL 2025 Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger ACL 2025 Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction ACL 2025 CoIR: A Comprehensive Benchmark for Code Information Retrieval Models ACL 2025 CodePRM: Execution Feedback-enhanced Process Reward Model for Code Generation ACL 2025 UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval COLING 2024 ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models ACL 2024 Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios ACL 2024 Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions ACL 2024 Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation ACL 2024 Improving Language Model Reasoning with Self-motivated Learning COLING 2024 Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment EMNLP 2023 KPT: Keyword-Guided Pre-training for Grounded Dialog Generation AAAI 2023 One Cannot Stand for Everyone! Leveraging Multiple User Simulators to train Task-oriented Dialogue Systems ACL 2023 MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions ACL 2023 Retrieval-free Knowledge Injection through Multi-Document Traversal for Dialogue Models ACL 2023 DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering ACL 2023 A Synthetic Data Generation Framework for Grounded Dialogues ACL 2023 HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks ACL 2023 Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues EMNLP 2023 Learning Summary-Worthy Visual Representation for Abstractive Summarization in Video IJCAI 2023 Offline-to-Online Co-Evolutional User Simulator and Dialogue System EMNLP 2022 Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation EMNLP 2022 Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark EMNLP 2022 Leveraging Only the Category Name for Aspect Detection through Prompt-based Constrained Clustering EMNLP 2022 AEG: Argumentative Essay Generation via A Dual-Decoder Model with Content Planning EMNLP 2022 Momentum Contrastive Pre-training for Question Answering EMNLP 2022 Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing EMNLP 2022 CoCA-MDD: A Coupled Cross-Attention based Framework for Streaming Mispronunciation Detection and Diagnosis INTERSPEECH 2022 LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework NAACL 2022 CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training NAACL 2022 UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation AAAI 2022 Sparse Structure Search for Delta Tuning NIPS 2022 CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog Systems AAAI 2022 Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation COLING 2022 UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues ACL 2022 Compilable Neural Code Generation with Compiler Feedback ACL 2022 Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger IJCNLP 2021 Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning IJCNLP 2021 Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger ACL 2021 Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning ACL 2021 Multi-Channel Reverse Dictionary Model AAAI 2020 Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association EMNLP 2017