Papers by Yi Cai

Controllable Abstractive Sentence Summarization with Guiding Entities (2020.coling-main)

Challenge:	Recent advances have extended DPO to multimodal scenarios, achieving strong performance.
Approach:	They propose to use a sentence-level preference optimization technique to optimize individual sentences for more precise preference optimization without additional models or parameters.
Outcome:	Experiments show that Adaptive Sentence-level Preference Optimization significantly improves the alignment of multimodal models.

Copied to clipboard

Changmeng Zheng, Yi Cai, Guanjie Zhang, Qing Li

Text Generation

Challenge:	Existing text summarization models lack guiding entities to ensure that entities are present in summaries.
Approach:	They propose a controllable abstractive sentence summarization model which generates summaries with guiding entities.
Outcome:	The proposed model outperforms the state-of-the-art models in evaluation scores and informativeness metrics.

A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation (2024.lrec-main)

Copied to clipboard

Li Yuan, Yi Cai, Haopeng Ren, Jiexin Wang

Updating Large Language Models’ Memories with Time Constraints (2024.findings-emnlp)

Challenge:	Existing models overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees.
Approach:	They propose a model that utilizes logical entailment patterns to generate coherent explanations by leveraging logical patterns.
Outcome:	The proposed model produces more coherent and reasonable conclusions that closely align with the underlying premises.

Copied to clipboard

Xin Wu, Yuqi Bu, Yi Cai, Tao Wang

Sequence Structure Aware Retriever for Procedural Document Retrieval: A New Dataset and Baseline (2025.findings-emnlp)

Challenge:	Large language models (LLMs) can modify their internal memory by incorporating the latest external knowledge, but in practical applications, outdated information may be inputted into LLMs.
Approach:	They propose a two-stage decoupling framework that separates the identification and computation of time constraints into a symbolic system and propose 'selective update' of internal memory based on time constraints.
Outcome:	The proposed framework improves ChatGPT performance by 60% and improves state-of-the-art LLM GPT-4.

Copied to clipboard

Zhenqi Ye, HaoPeng Ren, Yi Cai, Qingbao Huang, Jing Qin, Pinli Zhu, Songwen Gong

A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation (D18-1)

Challenge:	Existing retrieval methods neglect the execution sequence structures inherent in procedural documents.
Approach:	They propose a retrieval model which integrates procedural graphs with document representations.
Outcome:	The proposed model integrates procedural graphs with document representations to improve document retrieval.

Copied to clipboard

Jingjing Xu, Xuancheng Ren, Yi Zhang, Qi Zeng, Xiaoyan Cai, Xu Sun

Text Generation

Challenge:	Existing models for narrative story generation lack semantic dependency among sentences.
Approach:	They propose a skeleton-based model that generates the most critical phrases and expands them to a complete sentence.
Outcome:	The proposed model can generate significantly more coherent stories according to human evaluation and automatic evaluation.

Task-oriented Domain-specific Meta-Embedding for Text Classification (2020.emnlp-main)

Copied to clipboard

Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li

Beyond Code: Evaluate Thought Steps for Complex Code Generation (2024.lrec-main)

Challenge:	Existing methods neglect domain-specific knowledge and use the same word embedding for each word in all domain-specified datasets.
Approach:	They propose a method to incorporate domain-specific and task-oriented information into meta-embeddings by combining pre-trained word embeddings.
Outcome:	The proposed method performs well on four text classification datasets and shows that it is compatible with existing methods.

Copied to clipboard

Liuwen Cao, Yi Cai, Jiexin Wang, Hongkui He, Hailin Huang

Unlocking Human-Like Visible Logic: How Logic Diagrams Boost Logic Reasoning in Large Language Models? (2026.findings-acl)

Challenge:	Existing efforts to generate code in C++ rely on relatively simple programming problems . large language models (LLMs) pre-trained on numerous code data have opened up new opportunities for code generation.
Approach:	They propose a task that evaluates the quality of thought steps and code implementation . they construct a dataset of complex programming problems in C++ .
Outcome:	The proposed task evaluates the quality of thought steps and code implementation in a C++ programming language.

Copied to clipboard

Xin Wu, Yuqi Bu, Mengchen Zhao, Qingbao Huang, Yi Cai

Demystifying Small Language Models for Edge Deployment (2025.acl-long)

Challenge:	Recent advances in large language models (LLMs) have demonstrated their remarkable capabilities in natural language understanding and generation, but they struggle with formal logical reasoning.
Approach:	They propose to incorporate visual logic diagrams into LLMs’ reasoning workflows to enhance their performance on formal logic tasks.
Outcome:	The proposed model improves on syllogistic and conditional reasoning with programmatically generated Venn, Euler, and Linear diagrams.

Copied to clipboard

Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Wei Liu, Jian Luan, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu

Leveraging LLM Reasoning Enhances Personalized Recommender Systems (2024.findings-acl)

Challenge:	Small language models (SLMs) are a promising solution for resource-constrained devices such as smartphones and the Web of Things.
Approach:	They propose to use SLMs to build and optimize a set of small language models that are publicly accessible.
Outcome:	The proposed models outperform 7B models in general tasks, while their in-context learning capabilities remain limited and their efficiency has significant optimization potential.

Copied to clipboard

Alicia Tsai, Adam Kraft, Long Jin, Chenwei Cai, Anahita Hosseini, Taibai Xu, Zemin Zhang, Lichan Hong, Ed H. Chi, Xinyang Yi

SpecEdit: A Spectral Approach for Multi-Round Knowledge Editing (2026.findings-acl)

Challenge:	Recent advances have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting.
Approach:	They propose to use Large Language Models to perform tasks with subjectivity and personalized preferences as inputs to RecSys.
Outcome:	The proposed framework aligns with real human judgment on the coherence and faithfulness of LLM reasoning responses.

Copied to clipboard

Junxian Liu, Zikun Deng, Xin Wu, Dazhen Deng, Yi Cai

Explainability & Interpretability in NLP

Challenge:	Multi-round knowledge editing suffers from performance degradation as edits accumulate . intrinsic knowledge of model and historical edit memories are naively coupled during editing . SpecEdit improves model editing performance by reducing destructive coupling .
Approach:	They propose a spectral-based model editing module that integrates into existing editing methods without altering their original optimization procedures.
Outcome:	The proposed model improves performance on multiple LLMs and editing methods.

Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication (2025.findings-emnlp)

Copied to clipboard

Lewei Jin, Kui Zhang, Yongqi Chen, null Zhuoyifan, Renjie Li, Yi Gao, Bowei Yang, Zhengong Cai, Wei Dong

Green & Sustainable NLP

Challenge:	Large language models are reshaping internet services, and serving them is costly.
Approach:	They propose an efficient distributed LLM serving system that splits prefill and decode requests into smaller chunks .
Outcome:	The proposed system reduces TTFT, TPOT, and latency compared to the state-of-the-art system.

A Boundary-aware Neural Model for Nested Named Entity Recognition (D19-1)

Copied to clipboard

Changmeng Zheng, Yi Cai, Jingyun Xu, Ho-fung Leung, Guandong Xu

RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models (2025.findings-acl)

Challenge:	Existing methods for named entity recognition ignore nested entities . a boundary-aware neural model can locate entities precisely by detecting boundaries .
Approach:	They propose a boundary-aware neural model for nested named entity recognition which leverages entity boundaries to predict entity categorical labels.
Outcome:	The proposed model outperforms state-of-the-art methods on GENIA dataset . it captures dependencies of entity boundaries and categorical labels, which helps to improve identifying entities.

Copied to clipboard

Bihan Zhou, HaoPeng Ren, Li Yuan, Yi Cai, Liuwen Cao, Zikun Deng

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model (2025.findings-naacl)

Challenge:	Existing knowledge editing methods focus on instance-level editing, which is prone to knowledge degradation and general ability deterioration due to redundant instance-specific modifications.
Approach:	They propose a rule-level editing method that generalizes rule-derived knowledge to update rule-based instances.
Outcome:	The proposed method improves portability and performance over baselines for LLaMA-2-7B on RULEmix.

Copied to clipboard

Jiali Chen, Xusen Hei, Yuqi Xue, Zihan Wu, Jiayuan Xie, Yi Cai

RTADev: Intention Aligned Multi-Agent Framework for Software Development (2025.findings-acl)

Challenge:	Recent large language models (LLMs) overlook children’s reading preferences, which poses challenges in CLA.
Approach:	They propose a method that augments large language models with children's reading preferences for adaptation by obtaining characters' personalities and narrative structure as additional information for fine-grained instruction tuning.
Outcome:	The proposed method significantly improves performance in automatic and human evaluation.

Copied to clipboard

Jie Liu, Guohua Wang, Ronghui Yang, Jiajie Zeng, Mengchen Zhao, Yi Cai

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) are efficient assistants to humans in software development tasks, but they can cause errors during the development process.
Approach:	They propose an intention aligned multi-agent framework that ensures that all agents work based on a consensus.
Outcome:	The proposed framework reduces errors and improves the quality of generated software code.

Active Generalized Category Discovery with Diverse LLM Feedback (2026.eacl-long)

Copied to clipboard

Henry Peng Zou, Siffi Singh, Yi Nian, Jianfeng He, Jason Cai, Saab Mansour, Hang Su

DoTAT: A Domain-oriented Text Annotation Tool (2022.acl-demo)

Challenge:	Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabeled data using limited labeled data from known categories.
Approach:	They propose a framework for generalized category discovery that actively learns from diverse and collaborative feedback.
Outcome:	The proposed framework improves instance-level contrastive features, generates category descriptions, and aligns uncertain instances with LLM-selected category descriptions.

Copied to clipboard

Yupian Lin, Tong Ruan, Ming Liang, Tingting Cai, Wen Du, Yi Wang

Challenge:	DoTAT is a domain-oriented text annotation tool that can reduce the time for event annotation by 19.7% . the tool supports multi-person collaborative process with automatically merging and review .
Approach:	They propose a domain-oriented text annotation tool called DoTAT . it provides multi-person collaborative process with automatic merging and review .
Outcome:	The proposed tool can reduce the time for event annotation by 19.7% compared with existing tools.

IgSEG: Image-guided Story Ending Generation (2021.findings-acl)

Copied to clipboard

Qingbao Huang, Chuan Huang, Linzhang Mo, Jielong Wei, Yi Cai, Ho-fung Leung, Qing Li

CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction (2025.acl-long)

Challenge:	Existing tasks such as story ending generation generate text-based story endings, but visual storytelling generates photo-streams-based stories.
Approach:	They propose a task called Image-guided Story Ending Generation (IgSEG) given a multi-sentence story plot and an ending-related image, they propose MGCL to solve these challenges.
Outcome:	The proposed model outperforms baselines on automatic and human evaluation.

Copied to clipboard

Jiali Chen, Xusen Hei, HongFei Liu, Yuancheng Wei, Zikun Deng, Jiayuan Xie, Yi Cai, Li Qing

Mitigating Contradictions in Dialogue Based on Contrastive Learning (2022.findings-acl)

Challenge:	Computer-aided design (CAD) is crucial in prototyping 3D objects through geometric instructions.
Approach:	They propose a CAD review task to automatically detect and correct potential errors . they propose CAD program repairer framework to provide helpful feedback on error correction .
Outcome:	The proposed framework outperforms existing MLLMs in detecting errors and providing feedback on error correction.

Copied to clipboard

Weizhao Li, Junsheng Kong, Ben Liao, Yi Cai

Segment-Level and Category-Oriented Network for Knowledge-Based Referring Expression Comprehension (2023.findings-acl)

Challenge:	Current chatbots generate fluent, informative responses but sometimes generate contradictory responses when interacting with human.
Approach:	They propose to use contrastive learning technique to mitigate contradiction issues in chatbots by minimizing the similarity between the target response and contradiction related negative example.
Outcome:	The proposed method outperforms existing methods on automatic and human evaluation while preserving response fluency.

Copied to clipboard

Yuqi Bu, Xin Wu, Liuwu Li, Yi Cai, Qiong Liu, Qingbao Huang

Towards Exploiting Sticker for Multimodal Sentiment Analysis in Social Media: A New Dataset and Baseline (2022.coling-1)

Challenge:	Existing methods employ sentence-level retrieval and fusion methods, which may lead to similarity bias and interference from irrelevant information in unstructured knowledge sentences.
Approach:	They propose a segment-level and category-oriented network to solve similarity bias problem by segmenting and prompting knowledge retrieval methods and a category-based grounding method.
Outcome:	The proposed model eliminates similarity bias and improves the overall performance of the KB-REC task.

Copied to clipboard

Feng Ge, Weizhao Li, Haopeng Ren, Yi Cai

Sentiment Analysis

Challenge:	Sentiment analysis in social media is challenging because of the lack of context.
Approach:	They propose to use stickers to perform a multimodal sentiment analysis task using Chinese stickers.
Outcome:	The proposed model performs best compared with other models.

TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues (2025.findings-acl)

Copied to clipboard

Yubin Ge, Salvatore Romeo, Jason Cai, Raphael Shu, Yassine Benajiba, Monica Sunkara, Yi Zhang

Natural Language Interfaces

Challenge:	Temporal reasoning in multi-session dialogues presents a significant challenge which has been under-studied in previous temporal reasoning benchmarks.
Approach:	They propose to augment LoCoMo dialogues and create multi-choice QAs to construct a temporal reasoning evaluation task and a framework to enhance temporal thinking capabilities of LLM-agents.
Outcome:	The proposed framework significantly improves temporal reasoning performance compared to baseline methods, raising from 29.83 on GPT-4o via standard prompting to 77.67 via the proposed framework.

Constructing Procedural Graphs with Multiple Dependency Relations: A New Dataset and Baseline (2023.findings-acl)

Copied to clipboard

Haopeng Ren, Yushi Zeng, Yi Cai, Bihan Zhou, Zetao Lian

CADMate: Generating CAD Assembly Plan with Geometric Chain-of-Thought and Spatial Physical Rewards (2026.acl-long)

Challenge:	Existing methods to structure procedural knowledge focus on representing descriptive knowledge but ignore another commonsense knowledge-Procedural Knowledge.
Approach:	They propose to generate flow graphs from procedural documents by extracting sequential dependency between sentences and missing two important dependencies in procedural document.
Outcome:	The proposed method can generate flow graphs from unstructured documents with syntactic information and discourse structures.

Copied to clipboard

Jiali Chen, DingBa Fu, Xusen Hei, Yuhang Liu, Yiyang Chen, Jiayuan Xie, Wenqi Fan, Yi Cai

MemInsight: Autonomous Memory Augmentation for LLM Agents (2025.emnlp-main)

Challenge:	Computer-aided design (CAD) is crucial in prototyping complex 3D objects . designers manually define assembly sequences for individual CAD parts .
Approach:	They propose a framework for computer-aided design that predicts actions for CAD parts . they use a reference design image and disassembled parts to generate 6-DoF transformations .
Outcome:	The proposed framework outperforms existing MLLMs in the design of CAD assemblies.

Copied to clipboard

Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang, Yassine Benajiba

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding (2026.findings-acl)

Challenge:	Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools.
Approach:	They propose an autonomous memory augmentation approach to enhance semantic data representation and retrieval mechanisms by leveraging historical interactions.
Outcome:	The proposed approach outperforms a baseline RAG by 34% in recall for LoCoMo retrieval on three task scenarios and boosts persuasiveness of recommendations by 14%.

Copied to clipboard

Songcheng Cai, Zhiheng Lyu, Yuansheng Ni, Xiangchao Chen, Baichuan Zhou, Shenzhe Zhu, Yi Lu, Haozhe Wang, Chi Ruan, Benjamin Schneider, Weixu Zhang, Xiang Li, Andy Zheng, Yuyu Zhang, Ping Nie, Wenhu Chen

A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020.coling-main)

Challenge:	Existing benchmarks for agentic repository-level code understanding overlook long tail topics and rely on memorized knowledge.
Approach:	They propose a repository-level agentic code understanding benchmark that uses long-tail repositories with executable environments to enforce topical balance.
Outcome:	Empirically, a Qwen3-8B model trained with the proposed benchmark outperforms GPT-4o by 2.3 points.

Copied to clipboard

Haopeng Ren, Yi Cai, Xiaofeng Chen, Guohua Wang, Qing Li

Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models (2026.acl-long)

Challenge:	Existing supervised and distantly supervised RC models ignore the emergence of novel relations in open environment.
Approach:	They propose a two-phase prototypical network with prototype attention alignment and triplet loss to dynamically recognize the novel relations with a few support instances without catastrophic forgetting.
Outcome:	Experiments show that the proposed model performs better on deep learning and few-shot learning . it can recognize the novel relations with a few support instances without catastrophic forgetting .

Copied to clipboard

Boyan Han, Yiwei Wang, Yi Song, Yujun Cai, Chi Zhang

Rethinking-based Code Summarization with Chain of Comments (2025.coling-main)

Challenge:	Diffusion large language models (dLLMs) offer bidirectional attention and parallel generation . fixed anchors can enforce constraints, but they often impose rigid spans, leading to truncated reasoning .
Approach:	They propose a method that dynamically estimates end-anchor positions to adjust generation length before iterative infilling.
Outcome:	The proposed method improves format compliance and answer accuracy on GSM8K and MATH.

Copied to clipboard

Liuwen Cao, Hongkui He, Hailin Huang, Jiexin Wang, Yi Cai

Scene Graph Enhanced Pseudo-Labeling for Referring Expression Comprehension (2023.findings-emnlp)

Challenge:	Existing methods focus on learning a direct mapping from pure code to summaries, overlooking the heterogeneity gap between code and summary.
Approach:	They propose a framework that uses chain of comments as auxiliary intermediate information to bridge the gap between code and summaries.
Outcome:	The proposed framework outperforms baseline models and multiple code Large Language Models by a large margin.

Copied to clipboard

Cantao Wu, Yi Cai, Liuwu Li, Jiexin Wang

EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions (2026.findings-acl)

Challenge:	Referring expression comprehension is a visual-linguistic task that involves localizing objects in images based on textual referring expressions.
Approach:	They propose a scene graph-based framework that generates high-quality pseudo region-query pairs . their method captures relationships between objects in images and generates expressions enriched with relation information.
Outcome:	The proposed framework outperforms existing methods by 10%, 12%, and 11% on RefCOCO, RefCoCO+, and Ref COCOg datasets.

Copied to clipboard

Weiyu Sun, Liangliang Chen, Yongnuo Cai, Huiru Xie, Yi Zeng, Ying Zhang

Knowledge-Guided Cross-Topic Visual Question Generation (2024.lrec-main)

Challenge:	Multimodal Large Language Models (MLLMs) are a promising tool for traditional education but lack authentic and domain-specific benchmarks to accurately interpret student handwritten solutions.
Approach:	They propose to use MLLMs to interpret unconstrained STEM student handwritten solutions with intertwined mathematical formulas, diagrams, and textual reasoning to bridge this gap.
Outcome:	The proposed model can detect and rectify recognition errors with minimal human intervention on unseen student solutions.

Copied to clipboard

Hongfei Liu, Guohua Wang, Jiayuan Xie, Jiali Chen, Wenhao Fang, Yi Cai

Visual Data in NLP

Challenge:	Existing methods for visual question generation use answers or question types as constraints to generate questions.
Approach:	They propose a knowledge-guided cross-topic visual question generation task to generate unseen topics in cross-section scenarios.
Outcome:	The proposed model outperforms baselines and can generate unseen topic-related questions in cross-topic scenarios.

Grounded Multimodal Procedural Entity Recognition for Procedural Documents: A New Dataset and Baseline (2024.lrec-main)

Copied to clipboard

Haopeng Ren, Yushi Zeng, Yi Cai, Zhenqi Ye, Li Yuan, Pinli Zhu

Improve Decoding Factuality by Token-wise Cross Layer Entropy of Large Language Models (2025.findings-naacl)

Challenge:	Existing methods to extract procedural knowledge from documents focus on text-only settings, which is insufficient for entity disambiguation.
Approach:	They propose a model to detect the entity and the corresponding bounding box groundings in images.
Outcome:	The proposed model detects the entity and the corresponding bounding box groundings in image (i.e., visual entities) it is based on a dataset of a WikiHow 1 and EHow 2 document and the results are compared with existing models.

Copied to clipboard

Jialiang Wu, Yi Shen, Sijia Liu, Yi Tang, Sen Song, Xiaoyi Wang, Longjun Cai

Aligned Dual Channel Graph Convolutional Network for Visual Question Answering (2020.acl-main)

Challenge:	Large language models (LLMs) often struggle with the issue of generating inaccurate or fabricated content even when they possess correct knowledge.
Approach:	They propose a decoding method that mitigates hallucinations without extra training . they propose entropy eNhanced decoding that leverages inner probability changes .
Outcome:	The proposed method improves the truthfulness and informativeness of generation while maintaining robust QA accuracy.

Copied to clipboard

Qingbao Huang, Jielong Wei, Yi Cai, Changmeng Zheng, Junying Chen, Ho-fung Leung, Qing Li

Step Feasibility-Aware and Error-Correctable Entailment Tree Generation (2024.lrec-main)

Challenge:	Existing graph-based methods focus only on relations between objects in an image and neglect the importance of syntactic dependency relations between words.
Approach:	They propose a dual channel graph convolutional network to capture relations between objects in an image and syntactic dependency relations between words in a question.
Outcome:	The proposed model achieves comparable performance with the state-of-the-art approaches.

Copied to clipboard

Junyue Song, Xin Wu, Yi Cai

Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies (2026.acl-long)

Challenge:	Existing methods for generating entailment trees suffer from false feasible steps, resulting in error propagation.
Approach:	They propose an iterative entailment tree generation framework with step feasibility perception and state error handling mechanisms to enhance the interpretability of QA systems.
Outcome:	The proposed framework improves the interpretation of QA systems by demonstrating that it is feasible to choose steps that are false feasible and error propagating.

Copied to clipboard

Xudong Shen, li Yuan, Ye Chen, Xin Wu, Yi Cai, Zhiyong Wu

Robustness in NLP

Challenge:	Prior work has focused on the ability of Large Language Models to identify or classify fallacies, but their robustness against these fallacias in persuasive contexts remains largely unexplored.
Approach:	They propose a new metric to assess LLM robustness against fallacies by pairing factual questions with fallacious arguments and developing a multi-round debate framework to assess model resilience.
Outcome:	The proposed metric disentangles robustness from a model’s knowledge limitations and demonstrates unique vulnerability profiles across models.

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System (2022.acl-long)

Copied to clipboard

Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang

Recognizing Conflict Opinions in Aspect-level Sentiment Classification with Dual Attention Networks (D19-1)

Challenge:	Existing pre-trained language models often form a cascaded generation problem . this can lead to error accumulation across different sub-tasks and greater data annotation overhead.
Approach:	They propose a plug-and-play model for task-oriented dialogue that learns primary TOD task completion skills from heterogeneous dialog corpora.
Outcome:	The proposed model learns primary TOD task completion skills from heterogeneous dialog corpora.

Copied to clipboard

Xingwei Tan, Yi Cai, Changxi Zhu

Sentiment Analysis

Challenge:	Existing models ignore conflict opinions because they are sparse in the datasets.
Approach:	They propose a multi-label classification model with dual attention mechanism to address these problems by excluding conflict opinions from existing models.
Outcome:	The proposed model addresses the problem of exclusion of conflict opinions from the datasets.

SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)

Copied to clipboard

Ronghui Yang, Jie Liu, Jiajie Zeng, Jiexin Wang, Jiuchuan Jiang, Bo An, Yi Cai, Mengchen Zhao

Fine-Grained Features-based Code Search for Precise Query-Code Matching (2025.coling-main)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space.
Approach:	They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations.
Outcome:	The proposed framework outperforms baselines while maintaining reasonable time and computational costs.

Copied to clipboard

Xinting Zhang, Mengqiu Cheng, Mengzhen Wang, Songwen Gong, Jiayuan Xie, Yi Cai, Qing Li

TSDG: Content-aware Neural Response Generation with Two-stage Decoding Process (2020.findings-emnlp)

Challenge:	Existing methods to locate code snippets from databases represent the semantics of code and query by averaging the features of each token and word.
Approach:	They propose a fine-grained code search model that consists of a cross-modal encoder, mapping layer and classification layer to capture fine-granular interactions between code and query.
Outcome:	The proposed model significantly outperforms existing methods across multiple programming language datasets.

Copied to clipboard

Junsheng Kong, Zhicheng Zhong, Yi Cai, Xin Wu, Da Ren

Text Generation

Challenge:	Empirical results show that generative models often use a single decoder to generate a complete response at a stroke.
Approach:	They propose a content-aware model with two-stage decoding process to separate content words from function words.
Outcome:	The proposed model outperforms competing models in automatic and human evaluation on two datasets.

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)

Copied to clipboard

Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin

Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation (2025.acl-long)

Challenge:	Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations.
Approach:	They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments.
Outcome:	The proposed method has been deployed in a real-world commercial search system.

Copied to clipboard

Yuqi Bu, Xin Wu, Zirui Zhao, Yi Cai, David Hsu, Qiong Liu

Abstract-level Deductive Reasoning for Pre-trained Language Models (2024.lrec-main)

Challenge:	Existing VLMs are insensitive to information differences induced by slight perspective changes.
Approach:	They propose a visual perspective-taking task that requires robots to interpret human-centric instructions and identify corresponding objects from robot perspectives.
Outcome:	The proposed method improves performance by up to 18% and generalizes effectively to robotic and dynamic scenarios.

Copied to clipboard

Xin Wu, Yi Cai, Ho-fung Leung

MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement (2026.acl-long)

Challenge:	Existing methods fine-tune PLMs using the validity label and instance-level reasoning proofs as supervision signals.
Approach:	They propose to train PLMs to learn general reasoning patterns rather than instance-level knowledge by predicting the abstract reasoning proof of each sample.
Outcome:	The proposed model significantly reduces the impact of learning instance-level knowledge (over 70%)

Copied to clipboard

ZhenChun Xu, Yi Cai, Dajun Zheng, li Yuan, Mengchen Zhao, Qixiang Wang, Jiexin Wang

CMIG: Conceptual Metaphor Theory-Inspired Framework for Metaphorical Image Generation (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced automated program synthesis.
Approach:	They propose a model-adaptive and verification–enhanced framework for competition-level code generation that leverages adaptive assessment aligned with the model’s capabilities to select planning strategies while providing timely feedback and correction via multi-perspective verification.
Outcome:	The proposed framework outperforms existing state-of-the-art approaches on livecodebench, humanEval+, MBPP+, and codecontests, and achieves pass@1 results exceeding 3%–40%.

Copied to clipboard

Qingbao Huang, Cheng Yang, Jiawei Yao, Zhiyue Liu, Yi Cai, Xingmao Zhang

RTCFake: Speech Deepfake Detection in Real-Time Communication (2026.findings-acl)

Challenge:	Existing text-to-image systems often produce visually plausible but semantically literal outputs.
Approach:	They propose a structured prompting framework inspired by Conceptual Metaphor Theory . they propose to identify source–target mappings, filter projectable source attributes and select a visual realization strategy in a reproducible reasoning workflow.
Outcome:	The proposed framework improves semantic alignment and controllability on metaphor prompts.

Copied to clipboard

Jun Xue, Zhuolin Yi, Yihuan Huang, Yanzhen Ren, Yujie Chen, Cunhang Fan, Zicheng Su, Yongcheng Zhang, Bo Cai

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems (2025.findings-acl)

Challenge:	Existing detection studies focus on offline simulations and struggle to cope with complex distortions introduced during RTC transmission.
Approach:	They propose a large-scale speech deepfake dataset tailored for RTC scenarios . the dataset is constructed by transmitting speech through multiple social media and conferencing platforms .
Outcome:	The proposed dataset is constructed by transmitting speech through multiple mainstream social media and conferencing platforms, enabling precise pairing between offline and online speech.

Copied to clipboard

Yucheng Cai, Ke Li, Yi Huang, Junlan Feng, Zhijian Ou

Rethinking Multimodal Entity and Relation Extraction from a Translation Point of View (2023.acl-long)

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.

Copied to clipboard

Changmeng Zheng, Junhao Feng, Yi Cai, Xiaoyong Wei, Qing Li

Multilinguality

Challenge:	Special attention is paid to the cross-modal misalignment in text-image datasets which may mislead the learning.
Approach:	They propose a multimodal back-translation method which uses diffusion-based generative models for pseudo-paralleled pairs and a divergence estimator to construct a high-resource corpora as a bridge for low-ressource learners.
Outcome:	The proposed method outperforms 14 state-of-the-art methods in both entity and relation extraction tasks.

Where Confabulation Lives: Latent Feature Discovery in LLMs (2025.emnlp-main)

Copied to clipboard

Thibaud Ardoin, Yi Cai, Gerhard Wunder

Seq2Path: Generating Sentiment Tuples as Paths of a Tree (2022.findings-acl)

Challenge:	Despite advances in large language models, hallucination remains a critical failure mode . despite these advances, LLMs are prone to hallucinic outputs that contain illusory information presented as if it were factual or grounded in reality.
Approach:	They propose to isolate and analyze confabulation, a foundational aspect of hallucination, where the model fabricates facts about unknown entities.
Outcome:	The proposed method reveals that the model can fabricate facts with minimal disruption, shedding light on the inner representations that drive factual and non-factual output.

Copied to clipboard

Yue Mao, Yi Shen, Jingchao Yang, Xiaoying Zhu, Longjun Cai

Sentiment Analysis

Challenge:	Existing generative methods for extracting sentiment tuples do not have orders between the t-uples . a novel parallel generative framework for ABSA is proposed .
Approach:	They propose a parallel generative framework to generate sentiment tuples as paths of a tree . they train the model with an independent target and introduce a discriminative token .
Outcome:	The proposed method achieves state-of-the-art on AOPE, ASTE, TASD, UABSA, ACOS . it trains with the loss of ordinary Seq2Seq averaged over paths, and inferences automatically select valid paths.

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

Improving Named Entity Recognition via Bridge-based Domain Adaptation (2023.findings-acl)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Jingyun Xu, Changmeng Zheng, Yi Cai, Tat-Seng Chua

SAMULE: Self-Learning Agents Enhanced by Multi-level Reflection (2025.emnlp-main)

Challenge:	Existing methods for named entity recognition use pre-training language models to represent words, leading to entity type misclassification.
Approach:	They propose a model-agnostic framework called MoCL for cross-domain named entity recognition to refine the original representations and combine it with two distinct cross- domain NER methods and two pre-training language models to explore its generalization ability.
Outcome:	The proposed framework is model-agnostic and can be used to generalize and refine existing models.

Copied to clipboard

Yubin Ge, Salvatore Romeo, Jason Cai, Monica Sunkara, Yi Zhang

Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs (2024.findings-emnlp)

Challenge:	Modern AI agents rely on Large Language Models (LLMs) as their reasoning engines, but they still face the challenge of generating meaningful reflections due to inadequate error analysis and a reliance on rare successful trajectories.
Approach:	They propose a framework for self-learning agents powered by a retrospective language model that generates reflections during inference.
Outcome:	The proposed framework outperforms reflection-based baselines on three challenging benchmarks.

Copied to clipboard

Wenhua Cheng, Weiwei Zhang, Haihao Shen, Yiyang Cai, Xin He, Lv Kaokao, Yi Liu