Papers by Yi Cao
SILO-BENCH: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systems (2026.acl-long)
Copied to clipboard
Yuzhe Zhang, Feiran Liu, Yi Shan, Xinyi Huang, Xin Yang, Yueqi Zhu, Xuxin Cheng, Cao Liu, Ke Zeng, Terry Jingchen Zhang, Wenyuan Jiang
| Challenge: | Existing benchmarks conflate coordination ability with role-based priors. |
| Approach: | They propose a role-free benchmark for evaluating free-form collaboration under information silos. |
| Outcome: | The proposed benchmark systematically probes coordination capabilities under information silos using 54 configurations and 3 frontier LLMs. |
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages (2025.acl-long)
Copied to clipboard
Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Jan Philip Wahle, Terry Ruas, Meriem Beloucif, Christine de Kock, Nirmal Surange, Daniela Teodorescu, Ibrahim Said Ahmad, David Ifeoluwa Adelani, Alham Fikri Aji, Felermino D. M. A. Ali, Ilseyar Alimova, Vladimir Araujo, Nikolay Babakov, Naomi Baes, Ana-Maria Bucur, Andiswa Bukula, Guanqun Cao, Rodrigo Tufiño, Rendi Chevi, Chiamaka Ijeoma Chukwuneke, Alexandra Ciobotaru, Daryna Dementieva, Murja Sani Gadanya, Robert Geislinger, Bela Gipp, Oumaima Hourrane, Oana Ignat, Falalu Ibrahim Lawan, Rooweither Mabuya, Rahmad Mahendra, Vukosi Marivate, Alexander Panchenko, Andrew Piper, Charles Henrique Porto Ferreira, Vitaly Protasov, Samuel Rutunda, Manish Shrivastava, Aura Cristina Udrea, Lilian Diana Awuor Wanzare, Sophie Wu, Florian Valentin Wunderlich, Hanif Muhammad Zhafran, Tianhui Zhang, Yi Zhou, Saif M. Mohammad
| Challenge: | Emotion recognition is an umbrella term for several NLP tasks, but most work on high-resource languages has focused on low-resourced languages. |
| Approach: | They propose to use emotion recognition to describe perceived emotions in 28 different languages and across several domains to identify and annotate the datasets. |
| Outcome: | The proposed datasets cover low-resource languages from Africa, Asia, Eastern Europe, and Latin America, with instances labeled by fluent speakers. |
Soft Language Clustering for Multilingual Model Pre-training (2023.acl-long)
Copied to clipboard
| Challenge: | Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from the source language or when pre-training data is limited in size. |
| Approach: | They propose a method that contextually retrieves prompts as flexible guidance for encoding instances conditionally. |
| Outcome: | The proposed method improves on the XTREME task and also for low-resource languages in unsupervised sentence retrieval. |
Beyond Code: Evaluate Thought Steps for Complex Code Generation (2024.lrec-main)
Copied to clipboard
| 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. |
RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Models (2025.findings-acl)
Copied to clipboard
| 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. |
MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications (2024.emnlp-demo)
Copied to clipboard
Xiangru Tang, Chunyuan Deng, Hanminwang Hanminwang, Haoran Wang, Yilun Zhao, Wenqi Shi, Yi Fung, Wangchunshu Zhou, Jiannan Cao, Heng Ji, Arman Cohan, Mark Gerstein
| Challenge: | Large language models (LLMs) have evolved into interactive agents capable of planning, tool use, and task execution across various tasks. |
| Approach: | They propose a platform that leverages large language models to generate agent-tuning data for fine-tuneing smaller, specialized models. |
| Outcome: | MIMIR enables large models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2. |
SocialEval: Evaluating Social Intelligence of Large Language Models (2025.acl-long)
Copied to clipboard
Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, Leqi Lei, Yi Feng, Zexuan Xiong, Miao Yan, Xunzhi Wang, Yaru Cao, Jianing Yin, Shuai Wang, Quanyu Dai, Zhenhua Dong, Hongning Wang, Minlie Huang
| Challenge: | Existing work on LLMs does not address their social intelligence (SI) and their discrepancy with humans. |
| Approach: | They propose a script-based bilingual SI benchmark that integrates outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation by manually crafting narrative scripts. |
| Outcome: | The proposed model is based on a script-based bilingual evaluation paradigm that integrates outcome- and process-oriented evaluation by manually crafting narrative scripts. |
EpiGEN: An Efficient Multi-Api Code GENeration Framework under Enterprise Scenario (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to large language models fail to meet expectations for code generation tasks . existing approaches are faced with drawbacks of high resource consumption and inadequate handling of multi-API tasks. |
| Approach: | They propose an Efficient multi-Api code GENeration framework that uses private APIs to pre-train LLMs. |
| Outcome: | The proposed framework shows good acceptability and readability on single-GPU tasks compared to fully fine-tuned LLMs with a larger number of parameters. |
RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought (2025.acl-long)
Copied to clipboard
Yi Lu, Jiawang Cao, Yongliang Wu, Bozheng Li, Licheng Tang, Yangguang Ji, Chong Wu, Jay Wu, Wenbo Zhu
| Challenge: | Recent advances in multi-modal learning have enhanced MLLMs' ability to reason about visual content. |
| Approach: | They propose a framework that unifies multi-step multimodal reasoning with grounded visual understanding. |
| Outcome: | The proposed framework surpasses state-of-the-art methods by +6.5 gIoU and +9.2 cIou on ReasonSeg and achieves 49.7 mAP on SegInW under zero-shot settings. |
Neural Topic Modeling based on Cycle Adversarial Training and Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Neural topic models have been widely used to extract common topics across documents. |
| Approach: | They propose a framework to apply contrastive learning directly to the decoder . they propose 'self-supervised' contrastive loss to make the generator capture similar topic information . |
| Outcome: | The proposed framework outperforms baselines on four benchmark datasets. |
A Comparative Study on Schema-Guided Dialogue State Tracking (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work proposes using natural language descriptions to define domain ontologies for dialog state tracking. |
| Approach: | They propose to use natural language descriptions to define domain ontologies instead of tag names for each intent or slot . they introduce a set of newly designed bench-marking descriptions and show model robustness . |
| Outcome: | The proposed model is robust on homogeneous and heterogeneously described descriptions in training and evaluation. |
DeepGen: Diverse Search Ad Generation and Real-Time Customization (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Existing systems that generate ads manually are not effective in generating ad copy and generating millions of ads for large businesses. |
| Approach: | They propose a system that generates fluent ads from advertiser’s web pages in an abstractive fashion and solves practical issues such as factuality and inference speed. |
| Outcome: | The proposed system generates fluent ads from advertiser’s web pages in an abstractive fashion and solves practical issues such as factuality and inference speed. |
Rethinking-based Code Summarization with Chain of Comments (2025.coling-main)
Copied to clipboard
| 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. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
Aligning Large Language Models with Recommendation Knowledge (2024.findings-naacl)
Copied to clipboard
Yuwei Cao, Nikhil Mehta, Xinyang Yi, Raghunandan Hulikal Keshavan, Lukasz Heldt, Lichan Hong, Ed Chi, Maheswaran Sathiamoorthy
| Challenge: | Large language models (LLMs) excel at natural language reasoning, but cannot model complex user-item interactions inherent in recommendation tasks. |
| Approach: | They propose to equip large language models with recommendation-specific knowledge to address this gap by combining Masked Item Modeling and Bayesian Personalized Ranking (BPR) auxiliary task data samples are generated that encode item correlations and user preferences. |
| Outcome: | Experiments on Amazon Toys & Games, Beauty, and Sports & Outdoors show that the proposed method outperforms conventional and LLM-based baselines by significant margins in retrieval. |
TISE: A Tripartite In-context Selection Method for Event Argument Extraction (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent studies show that LLMs can finish inference by providing several examples. |
| Approach: | They propose a method which integrates three requirements when selecting an in-context example and integrates them into a set of determinantal point processes to enhance the reasoning capabilities of LLMs. |
| Outcome: | The proposed method can achieve superior performance with fewer examples and outperform some supervised methods. |
PIP: Perturbation-based Iterative Pruning for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are growing in size and complexity, causing significant challenges for their practical deployment in resource-constrained environments. |
| Approach: | They propose a double-view structured pruning method that combines information from two different views to iteratively prune those that struggle to distinguish between them. |
| Outcome: | The proposed method reduces the parameter count by approximately 20% while retaining over 85% of the original model’s accuracy across varied benchmarks. |
CLIO: Role-interactive Multi-event Head Attention Network for Document-level Event Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for document-level event extraction struggle due to two intrinsic challenges: nested arguments and multiple events. |
| Approach: | They propose a role-interactive multi-event head attention network to solve two challenges . they map different events to multiple subspaces and then determine whether the current event exists . |
| Outcome: | The proposed model improves on two widely used DEE datasets on the Internet. |
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Visual Document Retrieval (VDR) is of importance in multimodal retrieval applications. |
| Approach: | They propose a two-stage pruning and merging frameworks that combine pruning and merge techniques to achieve higher compression rates. |
| Outcome: | The proposed framework outperforms existing methods on 29 visual document retrieval datasets. |
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)
Copied to clipboard
Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao
| Challenge: | Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis. |
| Approach: | They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge. |
| Outcome: | The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks. |
Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are sensitive to the contextual position of information in input. |
| Approach: | They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions. |
| Outcome: | Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures. |
Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)
Copied to clipboard
Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang
| Challenge: | Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB). |
| Approach: | They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view. |
| Outcome: | The proposed framework achieves state-of-the-art on several entity linking benchmarks. |
TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models (2025.acl-industry)
Copied to clipboard
| Challenge: | Tabular data analysis is crucial in many scenarios, yet its complexity and density can make it challenging to determine the most appropriate analysis operations for a new table. |
| Approach: | They propose a tabular data analysis framework that recommends query-code-result triplets for new tables . they propose Rec-Align, a method to further improve recommendation quality . |
| Outcome: | The proposed framework achieves 77.0% top-5 recommendation recall on a dataset designed for tabular data analysis recommendation. |
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity. |
| Approach: | They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation. |
| Outcome: | The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. |
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)
Copied to clipboard
Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy . |
| Approach: | They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy. |
| Outcome: | The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training. |
Evolutionary Negative Module Pruning for Better LoRA Merging (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for integrating multiple low-rank Adaptation experts into a single backbone are limited by negative modules. |
| Approach: | They propose a plug-and-play LoRA pruning method to locate and exclude negative modules prior to merging. |
| Outcome: | The proposed method boosts the performance of existing merging algorithms across languages and vision domains. |