Papers by Di Zhou
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)
Copied to clipboard
Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao
| Challenge: | ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge. |
| Approach: | They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks . |
| Outcome: | ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering. |
Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition (P19-1)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is an important step in most natural language processing (NLP) applications. |
| Approach: | They propose a dual-adversarial neural transfer method for addressing low-resource Named Entity Recognition (NER) they propose 'Generalized Resource-Adversarial Discriminator' and 'accidental training' |
| Outcome: | The proposed method improves on low-resource Named Entity Recognition (NER) with two variants, i.e., DATNet-F and DATNET-P, and adversarial training is adopted to boost model generalization. |
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering (2020.acl-main)
Copied to clipboard
| Challenge: | Existing MCQA datasets are small in size, which increases difficulty of model learning and generalization. |
| Approach: | They propose a multi-source meta transfer framework for low-resource multiple-choice question answering . they extend meta learning by incorporating multiple training sources to learn a generalized feature representation across domains . |
| Outcome: | The proposed framework is independent of backbone language models and can bridge the distribution gap between training sources and target. |
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Current sycophancy research has largely overlooked its specific manifestations in the video-language domain. |
| Approach: | They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs. |
| Outcome: | The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks. |
Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Haonan He, Yuchen Ren, Yining Tang, Ziyang Xu, Junxian Li, Minghao Yang, Di Zhang, Yuan Dong, Tao Chen, Shufei Zhang, Yuqiang Li, Nanqing Dong, Wanli Ouyang, Dongzhan Zhou, Peng Ye
| Challenge: | Biology-Instructions is the first large-scale instruction-tuning dataset for multi-omics biological sequences. |
| Approach: | They propose a large-scale instruction-tuning dataset for multi-omics biological sequences . they propose 'chatMultiOmics' to overcome limitations of current LLMs on multi-ome tasks . |
| Outcome: | The proposed dataset bridges LLMs and complex biological sequence-related tasks while maintaining conversational fluency. |
Enhancing Auto-regressive Chain-of-Thought through Loop-Aligned Reasoning (2026.eacl-long)
Copied to clipboard
| Challenge: | Chain-of-Thought prompting is a powerful technique for enhancing language model’s reasoning capabilities, but generating long and correct CoT trajectories is challenging. |
| Approach: | They propose to align the steps of Chain-of-Thought reasoning with loop iterations and apply intermediate supervision during the training of Looped Transformers. |
| Outcome: | The proposed method generates accurate reasoning chains for complex problems exceeding training length, and improves performance of the auto-regressive model. |
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles (2020.acl-main)
Copied to clipboard
| Challenge: | Current summarization systems only produce plain, factual headlines, far from the practical needs for exposure and memorableness of the articles. |
| Approach: | They propose a task to generate relevant headlines with three style options . they propose combining summarization and reconstruction tasks into a multitasking framework . |
| Outcome: | The proposed method outperforms the state-of-the-art summarization model by 9.68% . it can generate relevant, fluent headlines with humor, romance and clickbait . |
BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge representation learning methods do not use graph contextualized knowledge. |
| Approach: | They propose to model subgraphs in a medical KG and integrate it with a pre-trained language model to do knowledge generalization. |
| Outcome: | The proposed model achieves state-of-the-art on several medical NLP tasks . it improves on MedERNIE, and the proposed model is effective . |
MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation (2026.acl-long)
Copied to clipboard
Dawei Wang, Di Zhao, Xinyuan Liu, Marci Chi Ma, Xiaoyang Liu, Chengming Zhou, Gary Ushaw, Richard Davison
| Challenge: | Embodied AI systems are open, where agents may leave or enter mid-task due to hardware failures or task-related errors. |
| Approach: | They propose a framework that reformulates credit assignment as a rank aggregation problem using contribution-based pairwise comparisons among agents generated by large multimodal models. |
| Outcome: | The proposed framework can guide agents toward effective cooperation in complex tasks of different types. |
Neural Relation Classification with Text Descriptions (C18-1)
Copied to clipboard
| Challenge: | State-of-the-art methods for relation classification suffer from data sparsity issue greatly. |
| Approach: | They propose a new neural relation classification method which integrates entities’ text descriptions into deep neural networks models. |
| Outcome: | The proposed method achieves much better experimental results than other state-of-the-art methods on the SemEval 2010 dataset. |
HyperText: Endowing FastText with Hyperbolic Geometry (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Empirically, we show that HyperText outperforms FastText on a range of text classification tasks with much reduced parameters. |
| Approach: | They propose a model that uses hyperbolic geometry to model tree-like hierarchies in natural language sentences by embedding words or ngrams in hyperbolical space. |
| Outcome: | Empirically, the proposed model outperforms FastText on a range of text classification tasks with much reduced parameters. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
Improving Model Factuality with Fine-grained Critique-based Evaluator (2025.acl-long)
Copied to clipboard
Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang
| Challenge: | Factuality evaluation aims to detect factual errors produced by language models and guide the development of more factual models. |
| Approach: | They propose a framework that leverages FenCE to improve the factuality of LM generators by constructing training data. |
| Outcome: | The proposed framework improves the factuality of LM generators by enhancing their training data. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
Copied to clipboard
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
| Challenge: | Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. |
| Approach: | They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations. |
| Outcome: | The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work. |
Robust Lottery Tickets for Pre-trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that pre-trained language models contain smaller matching subnetworks that are not robust to adversarial examples. |
| Approach: | They propose a method to find robust tickets hidden in pre-trained language models by learning binary weight masks and an adversarial loss objective to guide the search. |
| Outcome: | The proposed method improves on previous work on adversarial robustness evaluation. |
Meta-Task Prompting Elicits Embeddings from Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for large language modeling are based on task-related instructions or prompts. |
| Approach: | They propose a method for generating high-quality sentence embeddings from Large Language Models (LLMs) using meta-task prompts. |
| Outcome: | The proposed method produces high-quality sentences without fine-tuning . it excels on STS benchmarks and in downstream tasks, surpassing models with similar prompts . |
Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)
Copied to clipboard
Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen
| Challenge: | Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. |
| Approach: | They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
| Outcome: | The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
Density Matching for Bilingual Word Embedding (N19-1)
Copied to clipboard
| Challenge: | Recent approaches to cross-lingual word embeddings have been based on linear transformations between the embeddable vectors in the two languages. |
| Approach: | They propose a method that expresses two monolingual embedding spaces as probability densities and matches them using a Gaussian mixture model. |
| Outcome: | The proposed method can achieve competitive or superior performance on bilingual lexicon induction and cross-lingual word similarity data. |
Navigation as Attackers Wish? Towards Building Robust Embodied Agents under Federated Learning (2024.naacl-long)
Copied to clipboard
| Challenge: | Towards Byzantine-robust federated embodied agent learning, we study the attack and defense for the task of vision-and-language navigation (VLN) |
| Approach: | They propose a new method to defend against a navigation-and-language navigation attack using navigation as wish (NAW) the method provides the server with a 'prompt' of the vision-and language alignment variance between benign and malicious clients so they can be distinguished during training. |
| Outcome: | The proposed method outperforms other state-of-the-art defense methods on two VLN datasets. |
LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning (2026.findings-acl)
Copied to clipboard
Zhengjun Huang, Zhoujin Tian, Qintian Guo, Fangyuan Zhang, Yingli Zhou, Di Jiang, Zeying Xie, Xiaofang Zhou
| Challenge: | Large Language Models are constrained by limited context windows and lack of persistent memory . recent efforts address these limitations via external memory architectures . |
| Approach: | They propose an end-to-end agentic memory framework for real-time updating and retrieval that integrates hierarchical and temporal indexing layers. |
| Outcome: | The proposed framework outperforms established benchmarks in temporal reasoning, multi-session consistency, and retrieval efficiency. |
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)
Copied to clipboard
Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu
| Challenge: | Existing sparsification methods like pruning can lose model knowledge through parameter removal. |
| Approach: | They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks. |
| Outcome: | The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints. |
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding (2022.findings-emnlp)
Copied to clipboard
Jiahao Zhu, Daizong Liu, Pan Zhou, Xing Di, Yu Cheng, Song Yang, Wenzheng Xu, Zichuan Xu, Yao Wan, Lichao Sun, Zeyu Xiong
| Challenge: | Existing methods for temporal sentence grounding ignore two crucial issues . 1) Boundary-bias: the video downsampling process may lose these two frames . 2) Reasoning-biases: such incorrect new boundary frames lead to the reasoning bias . |
| Approach: | They propose a siamese sampling mechanism to generate additional contextual frames . they use a reasoning strategy to learn the inter-relationship among these frames a . |
| Outcome: | Extensive experiments demonstrate the effectiveness of a new siamese sampling network on three challenging datasets. |
LLaMA-Berry: Pairwise Optimization for Olympiad-level Mathematical Reasoning via O1-like Monte Carlo Tree Search (2025.naacl-long)
Copied to clipboard
Di Zhang, Jianbo Wu, Jingdi Lei, Tong Che, Jiatong Li, Tong Xie, Xiaoshui Huang, Shufei Zhang, Marco Pavone, Yuqiang Li, Wanli Ouyang, Dongzhan Zhou
| Challenge: | LLaMA-Berry is an advanced mathematical reasoning framework to enhance the problem-solving ability of large language models (LLMs). |
| Approach: | They propose a Monte Carlo Tree Search and Self-Refine framework to optimize reasoning paths and a pairwise reward model to evaluate different paths globally. |
| Outcome: | The proposed framework overcomes inefficiencies and limitations of step-wise and greedy search algorithms, enabling more efficient exploration of solution spaces. |
Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing reinforcement learning methods do not provide fine-grained supervision for complex reasoning tasks. |
| Approach: | They propose a reinforcement learning method that incorporates a generative model as the reward model and a token-level supervision model for RL training. |
| Outcome: | Experiments on 8 tasks show the proposed method is effective . |
Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models (2024.acl-long)
Copied to clipboard
Yuchong Sun, Che Liu, Kun Zhou, Jinwen Huang, Ruihua Song, Xin Zhao, Fuzheng Zhang, Di Zhang, Kun Gai
| Challenge: | Existing studies overlook the multi-turn instruction following ability of large language models (LLMs) Extensive experiments show that Parrot improves current LLMs by up to 7.2% in multi- turn instruction following. |
| Approach: | They propose a method for collecting multi-turn instructions that feature human-like queries, such as anaphora and ellipsis, and a context-aware preference optimization strategy to further enhance LLMs for complex queries. |
| Outcome: | The proposed method improves existing LLMs by up to 7.2% in multi-turn instruction following. |
Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou
| Challenge: | Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging . |
| Approach: | They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning. |
| Outcome: | The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets. |