Papers by Yuwei Zhang
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for retrieving encyclopedic knowledge lack a large corpus and effective commonsense retriever. |
| Approach: | They propose a framework for retrieval-augmented commonsense reasoning with a large commonsensense corpus and a commonseense retriever. |
| Outcome: | The proposed framework outperforms existing methods on commonsense reasoning tasks. |
CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence Translation (2022.findings-emnlp)
Copied to clipboard
Jian Yang, Shaohan Huang, Shuming Ma, Yuwei Yin, Li Dong, Dongdong Zhang, Hongcheng Guo, Zhoujun Li, Furu Wei
| Challenge: | Named entity recognition (NER) suffers from the scarcity of annotated training data, especially for low-resource languages without labeled data. |
| Approach: | They propose a cross-lingual entity projection framework to enable zero-shot cross-linguistic NER with the help of a multilingual labeled sequence translation model. |
| Outcome: | The proposed method outperforms the baseline method on two benchmarks by a large margin of +3 7 F1 scores and achieves state-of-the-art performance. |
A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots (2022.findings-acl)
Copied to clipboard
| Challenge: | Sub-Slot based task-oriented dialogs provide slot values segment by segment over multiple turns. |
| Approach: | They define a task called Sub-Slot based Task-Oriented Dialog (SSTOD) they build a Chinese dialog dataset SSD for boosting research on SSTOD. |
| Outcome: | The proposed task is called Sub-Slot based Task-Oriented Dialog (SSTOD) it includes 40K dialogs and 500K utterances from Chinese names, phone numbers, ID numbers and license plate numbers . the dataset is well annotated with sub-slot values, slot values, dialog states and actions . |
DANLI: Deliberative Agent for Following Natural Language Instructions (2022.emnlp-main)
Copied to clipboard
Yichi Zhang, Jianing Yang, Jiayi Pan, Shane Storks, Nikhil Devraj, Ziqiao Ma, Keunwoo Yu, Yuwei Bao, Joyce Chai
| Challenge: | Recent work on embodied AI agents that can perform tasks by following human language instructions is limited by reactive methods, which are insufficient for long-horizon complex tasks. |
| Approach: | They propose a neuro-symbolic deliberative agent that, while following language instructions, proactively applies reasoning and planning based on its neural and symbolic representations acquired from past experience. |
| Outcome: | The proposed agent achieves greater than 70% improvement over reactive baselines on the challenging TEACh benchmark. |
Multilingual Agreement for Multilingual Neural Machine Translation (2021.acl-short)
Copied to clipboard
| Challenge: | Existing models that only use auxiliary languages to encourage multilingual agreement ignore the relationships between different language pairs. |
| Approach: | They propose a multilingual agreement-based method which explicitly models the agreement between different translation directions by randomly substituting some fragments of the source language with their counterpart translations of auxiliary languages. |
| Outcome: | The proposed method improves on the multilingual translation task of 10 language pairs. |
ClusterLLM: Large Language Models as a Guide for Text Clustering (2023.emnlp-main)
Copied to clipboard
| Challenge: | Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of $0.6 per dataset. |
| Approach: | They propose a text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. |
| Outcome: | Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of $0.6 per dataset. |
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing long-term open-domain dialogue datasets lack complex, real-world personalization and fail to capture implicit reasoning. |
| Approach: | They propose a large-scale long-term dataset with 2,500 examples containing approximately 100 conversation sessions to study implicit reasoning in personalized dialogues. |
| Outcome: | The proposed model improves the ability of LLMs to reason over long-term conversations with implicit contextual dependencies. |
GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator (2023.acl-long)
Copied to clipboard
Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li
| Challenge: | Existing pre-training methods underutilize the benefits of language understanding for generation. |
| Approach: | They propose a GAN-style model for encoder-decoder pre-training with an auxiliary discriminator. |
| Outcome: | The proposed model outperforms existing pre-trained models and achieves state-of-the-art performance. |
Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for data augmentation generate new examples wildly without proper control, which hinders the usefulness of the proposed approach. |
| Approach: | They propose a chain-of-thought attribute manipulation approach that generates new data from existing examples by tweaking in the user-provided attribute. |
| Outcome: | The proposed approach generates new data from existing examples by tweaking in the user-provided, task-specific attribute, e.g., sentiment polarity or topic in movie reviews. |
A Parallelized Framework for Simulating Large-Scale LLM Agents with Realistic Environments and Interactions (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing work on large language models lacks a realistic environment and parallelized framework to support complex interactions between agents and environments. |
| Approach: | They propose a framework that integrates realistic societal environments and parallelized interactions to support simulations of large-scale agents. |
| Outcome: | The proposed framework can support simulations of 30,000 agents faster than the wall-clock time with 24 NVIDIA A800 GPUs and the performance increases linearly with the increase of LLM computational resources. |
Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities. |
| Approach: | They propose a plug-and-play module to enhance the performance of graph-based TKG models by exploring high-order histories step-by-step. |
| Outcome: | Experiments on three datasets and backbones show that CoH is effective in capturing high-order historical information for LLMs. |
Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to GMNER use MLLMs as auxiliary tools, causing cumulative error propagation and a lack of rigorous cross-modal verification. |
| Approach: | They propose a model that enforces structured cross-modal reasoning through Multi-style Reasoning Schema Injection and Constraint-guided Verifiable Optimization. |
| Outcome: | The proposed model enforces structured cross-modal reasoning through multi-style Reasoning Schema Injection and Constraint-guided Verifiable Optimization. |
Hawkes based Representation Learning for Reasoning over Scale-free Community-structured Temporal Knowledge Graphs (2025.coling-main)
Copied to clipboard
| Challenge: | Temporal knowledge graph reasoning is a useful tool for many practical tasks. |
| Approach: | They propose a Hawkes process-based Evolutional Representation Learning Network model which learns structural information and evolutional patterns of a TKG simultaneously. |
| Outcome: | The proposed model learns structural information and evolutional patterns of a TKG simultaneously, considering the characteristics of real-world networks: community structure, scale-free and temporal decaying. |
Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to solve non-deterministic reasoning problems in large language models are limited by their complexity and lack of a clear understanding of the problem. |
| Approach: | They propose a method to diagnose and correct non-deterministic reasoning behaviors in large language models. |
| Outcome: | The proposed method outperforms baselines and WebQSP benchmarks on the widely used WebQ SP and CWQ benchmarks. |
New Intent Discovery with Pre-training and Contrastive Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for identifying intents from unlabeled utterances are label-intensive, inefficient, and inaccurate. |
| Approach: | They propose a multi-task strategy to leverage unlabeled data and external labeled data for representation learning. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three intent recognition benchmarks. |
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders (2024.acl-long)
Copied to clipboard
| Challenge: | Conversational systems often rely on embedding models for intent classification and intent clustering tasks. |
| Approach: | They propose a toolkit that gives a more holistic view of intent embedding models by considering three tasks– (1) intent classification, (2) intent clustering, and (3) a novel triplet task. |
| Outcome: | The proposed model improves on the linguistic dimensions while affecting performance on downstream task metrics. |
Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that fine-tuning pre-trained language models with a small set of labeled utterances in a supervised manner is helpful, but it yields an anisotropic feature space, which may suppress the expressive power of the semantic representations. |
| Approach: | They propose to regularize supervised pre-training towards isotropy by contrastive learning and correlation matrix regularizers. |
| Outcome: | The proposed methods improve supervised pre-training by regularizing the feature space towards isotropy. |
Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake? (2023.findings-emnlp)
Copied to clipboard
Yuwei Bao, Keunwoo Yu, Yichi Zhang, Shane Storks, Itamar Bar-Yossef, Alex de la Iglesia, Megan Su, Xiao Zheng, Joyce Chai
| Challenge: | despite advances in AI, it remains a challenge to develop interactive task guidance systems that can offer situated, personalized guidance and assist humans in various tasks. |
| Approach: | They propose to use a multimodal benchmark dataset to study whether interactive task guidance systems can be quickly adapted to perceptually enabled tasks. |
| Outcome: | The proposed models demonstrate fair performances in some cases with no training . the results will provide a stepping stone for future work on situated task guidance . |
MACSum: Controllable Summarization with Mixed Attributes (2023.tacl-1)
Copied to clipboard
Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, Rui Zhang
| Challenge: | Existing work on controllable summarization with mixed attributes lacks designated annotations. |
| Approach: | They propose a human-annotated summarization benchmark for controllable summarizing with mixed attributes based on news and dialogue sources . |
| Outcome: | The proposed dataset contains human-annotated summarization datasets with mixed attributes . hard prompt models yield the best performance on most metrics and human evaluations . mixed-attribute control is still challenging for summarizing tasks . |
Learning Latent Relations for Temporal Knowledge Graph Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Temporal Knowledge Graph reasoning capture intra- and inter-time latent relations between entities that appear at different times. |
| Approach: | They propose a Latent relations Learning method for TKG reasoning that captures latent relations between entities at different times. |
| Outcome: | The proposed method exploits the intra- and inter-time latent relations of entities at different times. |
MetaTKG: Learning Evolutionary Meta-Knowledge for Temporal Knowledge Graph Reasoning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models rely on historical information to learn embeddings for entities, but ignore the evolution of facts. |
| Approach: | They propose a Temporal Meta-learning framework to learn evolutionary meta-knowledge from TKGs. |
| Outcome: | The proposed method improves on four widely-used datasets and three backbones on a wide range of scenarios on tKGs. |
FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)
Copied to clipboard
Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen
| Challenge: | Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. |
| Approach: | They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings. |
| Outcome: | The proposed framework achieves the strongest overall performance across all models. |
PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Instruction tuning has advanced large language models (LLMs) but its application in lower-resource languages faces challenges due to the imbalanced foundational abilities of LLMs across different languages. |
| Approach: | They propose a pivot language guided generation approach that utilizes a high-resource language as the pivot to enhance instruction tuning in lower-resourced languages. |
| Outcome: | The proposed approach improves instruction-following abilities of LLMs by 29% on average compared to directly responding in the target language alone. |
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs (2025.emnlp-main)
Copied to clipboard
Dayu Yang, Tianyang Liu, Daoan Zhang, Antoine Simoulin, Xiaoyi Liu, Yuwei Cao, Zhaopu Teng, Xin Qian, Grey Yang, Jiebo Luo, Julian McAuley
| Challenge: | Recent breakthrough models like OpenAI-o1 and DeepSeek-R1 show powerful task-solving capabilities, particularly advances in reasoning. |
| Approach: | They propose future research directions that may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence. |
| Outcome: | The proposed research may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence. |
MirrorCAPTCHA: Wild CAPTCHA, Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents (2026.acl-long)
Copied to clipboard
Xiangyu Wu, Yuwei Hu, Tianyu Cui, Yueying Tian, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Yang Yang, Jianfeng Lu
| Challenge: | Existing agent benchmarks fail to evaluate an agent's real-world capacity to handle CAPTCHA . Existing benchmarks ignore this practical challenge, failing to evaluate agents' ability to handle complex visual CAPTchas. |
| Approach: | They propose a benchmark annotated with Weighted Pass Rate and a new metric to measure agent's ability to handle CAPTCHA. |
| Outcome: | The proposed benchmark outperforms current state-of-the-art closed-source models on mirrorCAPTCHA and achieves 9.4% higher average weighted pass rate and 2.13% higher average Completion degree. |
Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection (2026.acl-long)
Copied to clipboard
Yuwei Zhang, Wenhao Yu, Shangbin Feng, Yifan Zhu, Letian Peng, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang
| Challenge: | Existing knowledge injection benchmarks for large language models lack standardized testing grounds. |
| Approach: | They propose a knowledge injection benchmark that leverages recently-added and expert-curated facts from Wikipedia’s “Did You Know...” entries. |
| Outcome: | The proposed framework improves reliability accuracy by 29.1%. |
Answer is All You Need: Instruction-following Text Embedding via Answering the Question (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for encoding instruction information fail to be sensitive to clearer criteria like “evaluate similarity based on emotion” . instead, we propose a different approach, which treats the instruction as a “question” about the input text and encodes the expected answers to obtain the representation accordingly. |
| Approach: | They propose a text embedder that captures characteristics of texts specified by user instructions clarifying the similarity criterion. |
| Outcome: | The proposed model improves instruction-following capabilities when applied to large language models and encoder-based LMs. |
Task Compass: Scaling Multi-task Pre-training with Task Prefix (2022.findings-emnlp)
Copied to clipboard
Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng
| Challenge: | Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. |
| Approach: | They propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. |
| Outcome: | The proposed model can be used as a foundation backbone for a wide range of tasks and as augmentation tool for data augmentation with complementary tasks. |
Effectiveness of Pre-training for Few-shot Intent Classification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing paradigms further pre-train language models such as BERT on vast amount of unlabeled corpus, but we find it highly effective and efficient to simply fine-tune BERT with roughly 1,000 labeled utterances from public datasets. |
| Approach: | They propose to fine-tune BERT with a small set of labeled utterances from public datasets to achieve a pre-trained model based on a set of 1,000 labeles. |
| Outcome: | The proposed model can outperform existing models on domains with very different semantics on novel domains. |
Improving Multilingual Neural Machine Translation with Auxiliary Source Languages (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has shown that translating from multiple source languages improves translation quality. |
| Approach: | They propose to exploit multiple source sentences from auxiliary languages to improve multilingual translation in a more common scenario by using synthetic multi-source corpora. |
| Outcome: | Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that the proposed model outperforms the baseline model significantly by +4.0 BLEU. |