Papers by Di Zhao

29 papers
Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to align large language models with human preferences are limited in generalizability due to distribution shift, preference label noise, and mismatch of challenging samples with model capacity.
Approach: They propose a framework that constructs preference pairs with varying difficulty levels and then produces a specific curriculum for reward model training.
Outcome: The proposed framework improves generalizability of reward models by a significant margin without incurring additional inference costs compared to existing non-curriculum baselines.
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models (2025.acl-demo)

Copied to clipboard

Challenge: Existing interpretation methods only support tasks with specific inputs, limiting their practical applications.
Approach: They propose an extensible module that matches different input data with interpretation methods and consolidates the interpreting outputs.
Outcome: The proposed module can match different input data with interpretation methods and consolidate the interpreting outputs.
ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for multimodal sentiment analysis focus on general knowledge, which is inadequate to identify specific sentiments across modalities.
Approach: They propose a method where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture.
Outcome: The proposed method outperforms all prior methods on three popular benchmarks on multimodal sentiment analysis metrics.
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)

Copied to clipboard

Challenge: Texar is an open-source text generation toolkit that supports a broad set of text generation tasks.
Approach: They introduce Texar, an open-source text generation toolkit that supports text generation tasks.
Outcome: Texar supports machine translation, summarization, dialog, content manipulation, and more.
TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for multimodal aspect-based sentiment analysis focus on fusing image regional information and textual words.
Approach: They propose a multimodal aspect-based sentiment analysis method that integrates regional and global image information with global image data.
Outcome: Experiments show that the proposed method outperforms state-of-the-art methods on two benchmark datasets.
Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for depression detection do not capture intra-theme and inter-themes correlation and do not allow clinicians to focus on themes of interest.
Approach: They propose an interactive depression detection framework that leverages in-context learning techniques to identify themes in clinical interviews and then models both intra-theme and inter-themes correlation.
Outcome: The proposed framework achieves 12% on Recall and 35% on F1-dep. metrics compared to the previous state-of-the-art model on the depression detection dataset DAIC-WOZ.
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.
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach: They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome: The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.
CPsyExam: A Chinese Benchmark for Evaluating Psychology using Examinations (2025.coling-main)

Copied to clipboard

Challenge: CPsyExam prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Approach: They propose a psychological benchmark, CPsyExam, constructed from questions from Chinese examination systems.
Outcome: The proposed benchmark prioritizes psychological knowledge and case analysis separately, recognizing the significance of applying psychological knowledge to real-world scenarios.
Finding the Dominant Winning Ticket in Pre-Trained Language Models (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies on pre-trained language models show that they can fine-tune parameters but achieve good downstream performance.
Approach: They find that a dominant winning ticket takes up 0.05% of the parameters and is transferable across different tasks.
Outcome: The proposed model can achieve comparable performance with the full-parameter model, the authors show . the dominant winning ticket takes up 0.05% of the parameters, and the model is transferable across tasks, they show - the authors conclude .
COLA: Collaborative Multi-Agent Framework with Dynamic Task Scheduling for GUI Automation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for implementing LLMs are limited by their complexity and lack fault tolerance mechanism.
Approach: They propose a scenario-aware agent Task Scheduler that decomposes task requirements into atomic capability units and dynamically selects the optimal agent from a decision agent pool.
Outcome: The proposed framework achieves competitive performance among GUI Agent methods with an average accuracy of 31.89% on the GAIA dataset.
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies attributed verbosity to biased labels, but new research shows that DPO can be effective in mitigating verboses.
Approach: They propose to use a method to reduce the amount of verbosity in LLMs by using a downsampling approach.
Outcome: The proposed approach overcomes the problem of verbosity by reducing the length reliance of the proposed algorithm.
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large language models achieve effective safety alignment at the time of release, but fine-tuning often compromises safety mechanisms.
Approach: They propose a method that performs safety realignment for large language models . they identify unsafe delta parameters from the fine-tuned models and recalibrate the retained parameters .
Outcome: The proposed method improves safety performance on safety benchmarks and jailbreak attacks while maintaining their performance on downstream tasks.
CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling (2024.findings-acl)

Copied to clipboard

Challenge: Existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence.
Approach: They propose a report-based multi-turn dialogue reconstruction framework for Chinese psychological counseling that uses large language models to assist counseling.
Outcome: The proposed framework is open-source and can be used in future research.
Let’s Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing efforts to improve CoT prompting have limitations that require extensive human effort or performance needs to be improved.
Approach: They propose a prompt approach for automatic reasoning called LBS3 inspired by curriculum learning which better reflects human learning habits.
Outcome: The proposed approach achieves strongly competitive performance compared to baselines in reasoning-intensive tasks with varying open- and closed-source LLMs.
Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization Framework (2026.acl-long)

Copied to clipboard

Challenge: Existing methods focus on isolated user histories, neglecting the essential role of inter-user differences.
Approach: They propose a framework that personalizes Large Language Models via preference-calibrated binary signals.
Outcome: The proposed framework outperforms baselines in a variety of personalization tasks and backbone LLMs.
LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization (2021.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models are trained based on single-grained tokenization, making it hard to learn the precise meaning of coarse-grain words and phrases.
Approach: They propose a language model pretraining method that incorporates multi-grained information of input text into pre-trained language models.
Outcome: The proposed method improves performance on CLUE and SuperGLUE in Chinese and English with little extra inference cost.
HMoE: Heterogeneous Mixture of Experts for Language Modeling (2025.emnlp-main)

Copied to clipboard

Challenge: Mixture of Experts (MoE) models use homogeneous experts with diverse capacities, resulting in a lack of expert specialization and parameter utilization.
Approach: They propose a framework where experts differ in size and possess diverse capacities . they propose HMoE to encourage frequent activation of smaller experts .
Outcome: The proposed framework outperforms homogeneous homogenous MoE models on evaluation benchmarks and achieves lower loss rate with fewer activated parameters.
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.
Improving Translation Quality Estimation with Bias Mitigation (2023.acl-long)

Copied to clipboard

Challenge: State-of-the-art translation Quality Estimation models are biased, relying on monolingual features while ignoring the bilingual semantic alignment.
Approach: They propose a method to mitigate the bias of translation quality estimation models by contrastive learning between clean and noisy sentence pairs.
Outcome: The proposed method improves the estimation performance while mitigating the bias.
Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for hierarchical text classification focus on modeling the text, but the concept of sharing among classes has been ignored in previous work.
Approach: They propose a concept-based method that explicitly represents the concept and model the sharing mechanism among classes for the hierarchical text classification.
Outcome: The proposed method outperforms state-of-the-art methods on two widely used datasets.
KMatrix: A Flexible Heterogeneous Knowledge Enhancement Toolkit for Large Language Model (2024.emnlp-demo)

Copied to clipboard

Challenge: Existing Knowledge-Enhanced Large Language Models (K-LLMs) toolkits focus on free-textual knowledge and lack robust datasets, models, and user-friendly experience.
Approach: They propose a flexible heterogeneous knowledge enhancement toolkit to enhance Large Language Models (LLMs) using external knowledge.
Outcome: KMatrix: a flexible heterogeneous knowledge enhancement toolkit for LLMs includes verbalizing-retrieval and parsing-query methods.
KMatrix-2: A Comprehensive Heterogeneous Knowledge Collaborative Enhancement Toolkit for Large Language Model (2025.emnlp-demos)

Copied to clipboard

Challenge: Existing studies on K-LLMs systems focus on declarative knowledge and procedural knowledge (rules) .
Approach: They propose to build a toolkit that supports comprehensive heterogeneous knowledge collaborative enhancement for Large Language Models (LLMs).
Outcome: The proposed toolkit provides unified knowledge integration and joint knowledge retrieval methods to achieve more comprehensive heterogeneous knowledge collaborative enhancement.
Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech (D19-3)

Copied to clipboard

Challenge: Language model adaptation (LMA) is a promising solution for conversational speech recognition systems.
Approach: They propose to use language model adaptation techniques to adapt language models to conversational speech recognition.
Outcome: The proposed toolkit compares state-of-the-art language model adaptation techniques in conversational speech recognition tasks.
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 .
Small Agent Can Also Rock! Empowering Small Language Models as Hallucination Detector (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies on hallucination detection rely heavily on closed-source LLMs such as GPT-4.
Approach: They propose an LLM-based agent framework called HaluAgent that integrates LLMs, multi-functional toolbox and a memory mechanism for hallucination detection.
Outcome: The proposed framework integrates the LLM, multi-functional toolbox, and can detect hallucinations on Chinese and English datasets.
MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL (2025.coling-main)

Copied to clipboard

Challenge: Recent LLM-based Text-to-SQL methods suffer from performance degradation on “huge” databases and complex user questions that require multi-step reasoning.
Approach: They propose a framework that integrates a decomposer agent and auxiliary agents to generate SQL queries from natural language text.
Outcome: The proposed framework achieves comparable execution accuracy on SQL-Llama tasks compared to the baseline model.
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.

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