Papers by Yucheng Li
With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models and Vision Language Model (VLMs) have demonstrated aptitude as potential substitutes for human participants in psycholinguistic experiments. |
| Approach: | They examine whether large language models and vision language models implicitly understand sound-based phenomena via orthography and imagery alone. |
| Outcome: | The proposed models demonstrate sound symbolism and ability to "hear" using language and vision modules. |
Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have demonstrated the potential of large language models (LLMs) for automatic error detection in math word problems (MWPs). |
| Approach: | They propose a framework that generates adaptive reference solutions using LLMs to enhance error detection by reducing conformity bias in MWPs. |
| Outcome: | The proposed framework mitigates the performance gap between conventional and alternative solutions in MWPs, especially when combined with reasoning-enhancing techniques like chain-of-thought prompting. |
Visual In-Context Learning for Large Vision-Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve the performance of Large Visual Language Models (LVLMs) are limited by cross-modal interactions and representation disparities. |
| Approach: | They propose a Visual In-Context Learning method that retrieves images via a 'Retrieval & Rerank' paradigm and summarises images with task intent and task-specific visual parsing to compose language-based demonstrations that reduce token count. |
| Outcome: | The proposed method reduces token count and alleviates cross-modal interaction problem on visual reasoning datasets. |
On the Rigour of Scientific Writing: Criteria, Analysis, and Insights (2024.findings-emnlp)
Copied to clipboard
| Challenge: | despite its importance, little work exists on modelling rigour in scientific writing . despite widespread use of term, scientific literature lacks definition of rigor . |
| Approach: | They propose a framework to automatically identify and define rigour criteria and assess their relevance in scientific writing. |
| Outcome: | The proposed framework can be tailored to the evaluation of scientific rigour for different areas. |
RIGOURATE: Quantifying Scientific Exaggeration with Evidence-Aligned Claim Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Scientific rigour tends to be sidelined in favour of bold statements, leading authors to overstate claims beyond what their results support. |
| Approach: | They propose a multimodal framework that retrieves supporting evidence from a paper and assigns each claim an overstatement score. |
| Outcome: | The proposed framework retrieves supporting evidence from ICLR and NeurIPS papers and assigns each claim an overstatement score. |
Compressing Context to Enhance Inference Efficiency of Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable power and impressive generalisation abilities across various tasks. |
| Approach: | They propose a method that prunes redundancies in the input context to make the input more compact. |
| Outcome: | The proposed method reduces memory and inference time while maintaining comparable performance compared to full context. |
ORANGE: Text-video Retrieval via Watch-time-aware Heterogeneous Graph Contrastive Learning (2023.emnlp-industry)
Copied to clipboard
Yucheng Lin, Tim Chang, Yaning Chang, Jianqiang Ma, Donghui Li, Ting Peng, Zang Li, Zhiyi Zhou, Feng Wang
| 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. |
Metaphor Detection via Explicit Basic Meanings Modelling (2023.acl-short)
Copied to clipboard
| Challenge: | Existing methods for metaphor detection use the aggregated meaning of a word to approximate its basic meaning. |
| Approach: | They propose a method which models the basic meaning of a word based on literal annotations and compares this with the contextual meaning in a target sentence to identify metaphors. |
| Outcome: | The proposed method outperforms the state-of-the-art method significantly in the F1 score and even reaches the theoretical upper bound on the VUA18 benchmark. |
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems. |
| Approach: | They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction. |
| Outcome: | The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets. |
PRAM: An End-to-end Prototype-based Representation Alignment Model for Zero-resource Cross-lingual Named Entity Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to address the named entity recognition problem are limited and lack explicit optimization specific to the task. |
| Approach: | They propose a prototype-based representation alignment model for a cross-lingual named entity recognition task using labeled source language data. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods in some challenging scenarios. |
COPNER: Contrastive Learning with Prompt Guiding for Few-shot Named Entity Recognition (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for Named Entity Recognition (NER) use a similarity metric to measure semantic similarity between test samples and referents, but their performance is limited due to the label scarcity. |
| Approach: | They propose a novel approach to learn a similarity metric for measuring the semantic similarity between test samples and referents, where each referent represents an entity class. |
| Outcome: | The proposed approach outperforms state-of-the-art models with a significant margin in most cases. |
Don’t Miss the Potential Customers! Retrieving Similar Ads to Improve User Targeting (2021.findings-emnlp)
Copied to clipboard
| Challenge: | a method for user targeting is developed to identify online users to whom an ad should be targeted. |
| Approach: | They propose a method for automatic augmentation of positive and negative clickthrough data for user targeting models. |
| Outcome: | The proposed method can increase positive and negative instances of positive training instances on two datasets. |
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 . |
LLM Inductive Reasoning Through Multi-Agent Enhanced Monte Carlo Tree Search (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for enhancing inductive reasoning of large language models often lack explicit optimization guidance and effective error correction. |
| Approach: | They propose a plug-and-play test-time framework that integrates multi-agent coordination with Monte Carlo Tree Search to improve inductive reasoning. |
| Outcome: | The proposed framework outperforms existing methods on four benchmarks and shows consistent improvements on QWQ-32B and Deepseek-V3 . |
Impromptu Cybercrime Euphemism Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for detecting euphemisms are ineffective in impromptu euphorism detection . Existing approaches for e-mail detection are limited to word-level ephemismals . |
| Approach: | They propose a framework for impromptu euphemism detection that integrates context augmentation and multi-round iterative training to better predict the actual meaning of a masked token. |
| Outcome: | The proposed framework improves 76-fold over the previous state-of-the-art euphemism detector. |
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)
Copied to clipboard
Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu
| Challenge: | Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data. |
| Approach: | They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs. |
| Outcome: | The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback. |
Hierarchical Region Learning for Nested Named Entity Recognition (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to recognize entities recursively from innermost to outermost are based on brute force and two-stage paradigms, often leading to cascaded errors. |
| Approach: | They propose a hierarchical region learning framework to automatically generate a tree hierarchy of candidate regions with nearly linear complexity and incorporate structure information into the region representation for better classification. |
| Outcome: | Experiments on benchmark datasets ACE-2005, GENIA and JNLPBA show that the proposed framework performs better than state-of-the-art models. |
Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks and contexts. |
| Approach: | They propose to use a token-level ensembling method to exploit the probability information at each generation step and to avoid early incorrect tokens. |
| Outcome: | The proposed method breaks the existing community performance ceiling and improves on several benchmarks. |
CM-Gen: A Neural Framework for Chinese Metaphor Generation with Explicit Context Modelling (2022.coling-1)
Copied to clipboard
| Challenge: | Nominal metaphors are commonly used in human language and have been shown to be effective in persuading, expressing emotion, and stimulating interest. |
| Approach: | They propose a multitask framework which optimizes three tasks: NM identification, NM component identification, and NM generation. |
| Outcome: | The proposed framework outperforms baselines on consistency and creativity on the NM generation task in Chinese. |
From Knowing to Teaching: Scaffolding Pedagogical Decisions for LLM Agent (2026.acl-long)
Copied to clipboard
Yucheng Wang, Shen Yang, Jifan Yu, Haoxuan Li, Joy Jia Yin Lim, Daniel Zhang-Li, Huiqin Liu, Lei Hou, Juanzi Li, Bin Xu
| Challenge: | Large language models produce content lacking pedagogical depth when asked to generate lessons . |
| Approach: | They propose a framework that allows teachers to select content according to pedagogical intent and sequence topics so foundations precede applications. |
| Outcome: | The framework achieves 67.8% win rate in human evaluation and 79.6% in LLM-based evaluation against eight baselines. |
Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge retrieval methods fail to account for interrelationship between knowledge pieces . however, current methods fail in a situation where multiple knowledge pieces are relevant . |
| Approach: | They propose an energy-based retriever that directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately. |
| Outcome: | The proposed retriever outperforms the baseline energy-based retriever in knowledge retrieval tasks. |
Metaphor Detection with Effective Context Denoising (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing models focus on semantically relevant information and provide a target-oriented parse tree structure for metaphor detection. |
| Approach: | They propose a new model which introduces a target-oriented parse tree structure for metaphor detection. |
| Outcome: | The proposed model achieves state-of-the-art on several main metaphor datasets and compares with other methods. |
FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing models for concept-level metaphor detection lack explicit knowledge of FrameNet . Metaphor detection is a pervasive linguistic device that is used in cognitive and communicative functions of language. |
| Approach: | They propose a BERT-based model that explicitly learns FrameNet Embeddings for metaphor detection. |
| Outcome: | The proposed model is more explainable and interpretable than existing models. |
UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent studies have shown that multi-task instruction tuning after pre-training greatly improves the model’s robustness and transfer ability, which is crucial for building a high-quality dialog system. |
| Approach: | They propose to use Task-aware Automatic Prompt generation (TAP) to automatically generate high-quality prompts from 15 dialog-related tasks. |
| Outcome: | The proposed model is robust to input prompts and capable of various dialog-related tasks. |
Safety Alignment via Constrained Knowledge Unlearning (2025.acl-long)
Copied to clipboard
Zesheng Shi, Yucheng Zhou, Jing Li, Yuxin Jin, Yu Li, Daojing He, Fangming Liu, Saleh Alharbi, Jun Yu, Min Zhang
| Challenge: | Existing defense mechanisms have not fully deleted harmful knowledge in large language models (LLMs) Existing methods to address safety alignment have not completely deleted harmful information in LLMs. |
| Approach: | They propose a safety alignment strategy that uses scoring neurons to identify useful knowledge in LLMs and pruning the gradients of neurons in U to preserve beneficial information. |
| Outcome: | The proposed method significantly improves model safety while maintaining utility compared to existing methods. |
An Open-Source Data Contamination Report for Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing contamination analysis is conducted internally by large language model developers and lacks transparency and completeness. |
| Approach: | They present a data contamination report for 15 popular large language models . they propose an open-source pipeline to perform contamination analysis on customised data . |
| Outcome: | The proposed pipeline enables the community to perform contamination analysis on customised data and models. |