Papers by Zhichao Yang

17 papers
Fast and Effective On-Policy Distillation from Reasoning Prefixes (2026.findings-acl)

Copied to clipboard

Challenge: On-policy distillation (OPD) requires expensive on-the-fly sampling of the student policy during training, which substantially increases training cost.
Approach: They propose to use on-policy distillation to sample trajectories from student model . they propose to terminate the sampling early during distillation .
Outcome: The proposed method matches the performance of full OPD in long reasoning outputs while reducing training FLOP by 2x–40x.
README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP (2024.findings-emnlp)

Copied to clipboard

Challenge: a new task is to generate lay definitions of medical terms in EHRs that are difficult to understand for patients.
Approach: They propose a task of automatically generating lay definitions to simplify medical terms into patient-friendly lay language.
Outcome: The proposed model can match or surpass state-of-the-art closed-source large language models like ChatGPT with high-quality data.
MedQA-CS: Objective Structured Clinical Examination (OSCE)-Style Benchmark for Evaluating LLM Clinical Skills (2026.eacl-long)

Copied to clipboard

Challenge: Current clinical LLM benchmarks fail to evaluate advanced clinical skills in AI and large language models (LLMs).
Approach: They propose a framework to evaluate large language models (LLMs) using two instruction-following tasks designed to reflect real clinical scenarios.
Outcome: The proposed framework evaluates LLMs through two instruction-following tasks designed to reflect real clinical scenarios.
Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Text (2025.emnlp-main)

Copied to clipboard

Challenge: Existing SBDH datasets lack detailed annotations and are limited in their availability and coverage.
Approach: They propose a synthetic SBDH annotation dataset with detailed SBDH status, temporal information, and rationale across 15 categories.
Outcome: The proposed dataset outperforms models with no Synth-SBDH training on three tasks using real-world clinical datasets from two distinct hospital settings.
Large Language Models are In-context Teachers for Knowledge Reasoning (2024.findings-emnlp)

Copied to clipboard

Challenge: In-context teaching is a method of providing in-concept example rationales to a student to reason over unseen cases.
Approach: They propose to use an LLM's self-elicited explanations as in-context demonstrations to prompt a student to reason over unseen cases.
Outcome: The proposed model outperforms human-crafted demonstrations on medical question answering and human-created models outperfect human-made demonstrations.
Interpretable Math Word Problem Solution Generation via Step-by-step Planning (2023.acl-long)

Copied to clipboard

Challenge: Existing approaches to solving math word problems focus on obtaining the correct answer.
Approach: They propose a step-by-step planning approach for intermediate solution generation that strategically plans the generation of the next solution step based on the MWP and the previous solution steps.
Outcome: The proposed approach improves the accuracy and interpretability of the solution on automatic metrics and human evaluation.
Generating Accurate Electronic Health Assessment from Medical Graph (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing models based on medical domain-specific knowledge or patients’ prior diagnoses and clinical encounters were mainly based upon clinical diagnoses.
Approach: They propose a graph neural network model that incorporates clinical knowledge into an end-to-end corpus-learning system and builds on it.
Outcome: The proposed model significantly improves the BLEU and rouge score compared with baseline models and physicians’ evaluation showed that it generates high-quality assessments.
NoteChat: A Dataset of Synthetic Patient-Physician Conversations Conditioned on Clinical Notes (2024.findings-acl)

Copied to clipboard

Challenge: NoteChat is a cooperative multi-agent framework for generating patient-physician dialogues . evaluator finds it outperforms state-of-the-art models for generating clinical notes . clinical documentation is largely done by physicians at both steps .
Approach: They propose a cooperative multi-agent framework leveraging Large Language Models to generate patient-physician dialogues.
Outcome: The proposed framework outperforms state-of-the-art models for generating clinical notes . it can engage patients directly and help clinical documentation, a leading cause of physician burnout .
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says .
Approach: They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions.
Outcome: a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures .
MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback (2025.naacl-long)

Copied to clipboard

Challenge: Generating multiple-choice questions (MCQG) for professional exams is challenging due to outdated knowledge, hallucination issues, and prompt sensitivity.
Approach: They propose a framework for converting medical cases into high-quality USMLE-style questions using a self-refine-based framework.
Outcome: The proposed framework improves human expert satisfaction regarding quality and difficulty of medical questions.
Generating Classical Chinese Poems from Vernacular Chinese (D19-1)

Copied to clipboard

Challenge: Existing models for classical Chinese poetry generation only allow users to use keywords to interfere with the meaning of generated poems.
Approach: They propose a model to generate classical Chinese poems from vernacular . their model uses unsupervised machine translation to generate Chinese poems . human evaluation shows it can generate high-quality poems comparable to amateur poems - authors .
Outcome: The proposed model improves the perplexity and BLEU of the proposed model compared with typical models and human evaluation shows it generates high-quality poems comparable to amateur poems.
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis (2025.findings-acl)

Copied to clipboard

Challenge: Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own . limited available data and deficient diversity in current datasets hinder study of parody .
Approach: They build a dataset of parody users and annotated comments from both English and Chinese corpora to test parody detection and comment sentiment analysis.
Outcome: The proposed datasets provide richer contextual information, which is lacking in existing datasets.
Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information (2023.acl-long)

Copied to clipboard

Challenge: Visual Word Sense Disambiguation (VWSD) is a task to find the image that most accurately depicts the correct sense of the target word for the given context.
Approach: They propose an unsupervised approach that incorporates sense definitions when sense information of the answer is not provided.
Outcome: The proposed approach improves the performance of the existing definition generation method in OOD examples.
Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for ICD coding are limited due to the high-dimensional space of multi-label assignment and the long-tail challenge.
Approach: They propose a prompt-based fine-tuning technique with label semantics to solve this challenge.
Outcome: The proposed method outperforms state-of-the-art methods on a benchmark dataset of code assignment in 14.5% of cases.
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing work aims to improve reasoning accuracy and factual integrity across large language models for knowledge-intensive tasks such as medical and commonsense reasoning.
Approach: They propose a versatile extension to the mutual reasoning framework (rStar) that enhances reasoning accuracy and factual integrity across large language models.
Outcome: The proposed extension to the mutual reasoning framework improves reasoning accuracy and factual integrity across large language models for complex, knowledge-intensive tasks.
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks (2026.findings-acl)

Copied to clipboard

Challenge: Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications.
Approach: They propose a framework that retrieves context from a memory bank to enhance alignment . they propose EMI-based approach to align vision and language models .
Outcome: The proposed framework reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead.
DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis (2026.acl-demo)

Copied to clipboard

Challenge: Existing synthetic data tools are limited by convoluted workflows, fragmented data standards, and limited scalability across modalities.
Approach: They develop an open-source framework that aims to reduce the technical barrier to synthetic data generation and subsequent model training.
Outcome: The proposed framework achieves an optimal balance between generation efficiency and data quality.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations