Papers by Di Zhou

26 papers
ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

Copied to clipboard

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

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

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

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

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

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

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

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

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

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

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

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations