Papers by Zhiyi Li

12 papers
HuatuoGPT, Towards Taming Language Model to Be a Doctor (2023.findings-emnlp)

Copied to clipboard

Challenge: Experimental results show that the distilled language model outperforms its teacher model (ChatGPT) in most cases.
Approach: They propose a Large Language Model (LLM) that leverages both distilled data from **ChatGPT** and real-world data from**doctors** in the supervised fine-tuning stage.
Outcome: The proposed model outperforms the teacher model in most cases by using additional real-world data and RLMF to align the language model with the merits of both sources.
PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree (2025.findings-naacl)

Copied to clipboard

Challenge: Recent methods for detecting LLM-generated text have shown impressive performance, but in real-world scenarios, users often introduce perturbations to the text.
Approach: They propose a method that detects syntactic trees that are minimally affected by perturbations and exhibit distinct differences between human-written and LLM-generated text.
Outcome: The proposed method shows that it is significantly better against perturbations on the HC3 and GPT-3.5-mixed datasets and also has the shortest time expenditure.
ORANGE: Text-video Retrieval via Watch-time-aware Heterogeneous Graph Contrastive Learning (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for text-video retrieval focus on informative representations and delicate matching mechanisms, but real-world scenarios often involve brief, ambiguous queries and low-quality videos.
Approach: They propose a novel method to learn informative embeddings for queries and videos . they use a watch-time-aware contrastive learning paradigm to capture dependencies .
Outcome: The proposed method is effective in a real-world video-search service.
How do LLMs’ Preferences Affect Event Argument Extraction? CAT: Addressing Preference Traps in Unsupervised EAE (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to supervised EAE suffer from preference traps due to misalignments between prior knowledge, instructions, or output constraints and LLMs’ preferences.
Approach: They propose an unsupervised EAE framework that handles LLMs' preference traps by targeting their prior knowledge and instructions.
Outcome: The proposed framework matches the best DeepSeek-R1 API model with a significantly lower time cost.
A Coarse-to-Fine Prototype Learning Approach for Multi-Label Few-Shot Intent Detection (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for few-shot intent detection are limited due to data scarcity and lack of information for unseen domains.
Approach: They propose to enhance utterance representations with label synset augmentation and refine prototypes by distilling coarse domain knowledge from a universal teacher model.
Outcome: The proposed approach outperforms existing methods in terms of accuracy and generalization across domains.
Cross-Document, Cross-Language Event Coreference Annotation Using Event Hoppers (L18-1)

Copied to clipboard

Challenge: Defined event hoppers for the DEFT Rich Entities, Relations and Events (Rich ERE) annotation task.
Approach: They propose an approach for cross-document, cross-lingual event coreference for the DEFT Rich Entities, Relations and Events (Rich ERE) annotation task.
Outcome: The proposed approach is based on the definition of event hoppers for the DEFT rich entities, relations, events and their attributes . it yields 389 cross-document event hoppings in 505 documents in three languages .
Huatuo-26M, a Large-scale Chinese Medical QA Dataset (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models are a powerful tool for medical research, but the data is a bottleneck.
Approach: They propose to use the largest ever medical Question Answering dataset with 26 Million QA pairs as a fine-tuning data for training large language models.
Outcome: The proposed dataset demonstrates that it can be used to train large language models and improves zero-shot performance on other datasets.
MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)

Copied to clipboard

Challenge: Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences.
Approach: They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge.
Outcome: The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria.
Contextual Representation Learning beyond Masked Language Modeling (2022.acl-long)

Copied to clipboard

Challenge: masked language models adopt sampled embeddings as anchors to estimate and inject contextual semantics to representations.
Approach: They propose a representation learning approach that uses embeddings as anchors to model contextual representations.
Outcome: The proposed model achieves 5x speedup and 1.2 points average improvement over MLM.
CMB: A Comprehensive Medical Benchmark in Chinese (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) provide a great breakthrough in medicine, says a new study . existing studies on LLMs leverage subjective evaluation, but evaluation in medicine is professional .
Approach: They propose a localized medical benchmark in Chinese rooted in native Chinese . they propose to use traditional Chinese medicine to evaluate large-scale LLMs .
Outcome: a new benchmark is developed to evaluate large-scale LLMs in china . the proposed model is rooted in the native Chinese linguistic and cultural framework .
StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs (2026.findings-acl)

Copied to clipboard

Challenge: Prior work focused on typographic and pixel-level perturbations, leaving the study of SCO unexplored.
Approach: They propose a framework that exploits MLLMs' diagrammatic reasoning capabilities to bypass safety guardrails.
Outcome: The proposed framework exploits the model's reasoning capabilities to bypass safety guardrails.
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks.
Approach: They propose a framework that exploits AdVersArial meTAphoR to induce LLMs to calibrate harmful metaphors for jailbreaking.
Outcome: The proposed framework can successfully jailbreak Large Language Models (LLMs) by leveraging the AdVersArial meTAphoR (AVATAR) framework achieves state-of-the-art attack success rate across multiple advanced LLMs.

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