Papers by Jiang Du

22 papers
S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech Models (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach: They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome: The proposed system enables more natural, robust, and human-aligned speech agents.
Unveiling Project-Specific Bias in Neural Code Models (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) based neural code models struggle to generalize effectively to real-world inter-project out-of-distribution data.
Approach: They propose a Cond-Idf measurement to measure the relatedness of a token with a label and its project-specificness.
Outcome: The proposed framework improves both inter-project OOD generalization and adversarial robustness while not sacrificing accuracy on intra-project IID data.
Dynamic Parallel Tree Search for Efficient LLM Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Recent methods focus on search accuracy while overlooking computational efficiency.
Approach: They propose a parallelism framework that dynamically optimizes reasoning path in inference.
Outcome: The proposed framework improves efficiency by 2-4 on average while maintaining or even surpassing existing reasoning algorithms in accuracy.
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing (2024.findings-acl)

Copied to clipboard

Challenge: Current benchmarks focus on coarse-grained knowledge, leaving the intricacies of fine-grounded knowledge unexplored.
Approach: They propose a benchmark and dataset specifically designed for FG multimodal entity knowledge editing.
Outcome: The proposed benchmark underscoring the complexity of FG knowledge editing in MLLMs.
MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for Large Multimodal Models (LMMs) are constrained by static representations, inadequately evaluating their ability to understand time-sensitive knowledge.
Approach: They propose a benchmark containing 2,104 time-sensitive knowledge samples spanning six knowledge types to evaluate temporal awareness along 6 key dimensions and 11 challenging tasks.
Outcome: The proposed benchmark measures temporal awareness along 6 key dimensions and 11 tasks, while most open-source LMMs still lack time understanding ability.
Data-Efficient Selection via Grammatical Complexity in Continual Pre-training of Domain-Specific LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Existing data selection strategies for continual pre-training of large language models often rely on scarce labeled data or computationally expensive LLMs.
Approach: They propose an annotation-independent data selection framework for CPT that evaluates grammatical complexity using lexical diversity and syntactic complexity.
Outcome: The proposed framework outperforms baselines on a financial dataset and surpasses full-data training by 1.7% using only 20% of the data.
SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for automating vulnerability repair suffer from syntactic overfitting . nvd published 49,230 Common Vulnerabilities and Exposures (CVE) records in 2025 alone .
Approach: They propose a semantic-aware reward framework that optimizes for code semantic equivalence rather than lexical mimicry.
Outcome: The proposed framework outperforms state-of-the-art frameworks on repository-level splits . it incorporates expert-aligned reasoning mechanism that grounds patch generation in structured diagnosis.
From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities (2025.findings-acl)

Copied to clipboard

Challenge: MLLMs are able to integrate multiple modalities into a single model to tackle complex tasks in real-world scenarios.
Approach: They propose a comprehensive survey of Omni-MLLMs to address the challenges and opportunities of multimodal modeling.
Outcome: The proposed model can integrate multiple modalities into a single model and provide novel perspectives.
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer (2025.acl-long)

Copied to clipboard

Challenge: Foundational models and their checkpoints have advanced deep learning, boosting performance across applications.
Approach: They propose a method for pruning fine-tuned models by calculating differences between them and original model.
Outcome: The proposed method can improve performance across vision, NLP, and multi-modal benchmarks.
Eliciting Knowledge from Experts: Automatic Transcript Parsing for Cognitive Task Analysis (P19-1)

Copied to clipboard

Challenge: Cognitive task analysis (CTA) is a type of analysis used to elicit and represent the knowledge and thought processes of domain experts.
Approach: They propose a weakly-supervised framework for automated CTA transcript parsing . they partition the parser process into a sequence labeling task and a text span-pair relation extraction task with distant supervision from human-curated protocol files.
Outcome: The proposed framework reduces human labor and scales the task to a small scale.
VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models have been widely applied to standard benchmarks due to the limited resources available in a domain.
Approach: They propose a Transformer-based language model called VarMAE for domain-adaptive language understanding that encodes the context of a token into a smooth latent distribution.
Outcome: Experiments on science- and finance-domain NLU tasks show that the proposed model can be efficiently adapted to new domains with limited resources.
SciEvent: Benchmarking Multi-domain Scientific Event Extraction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing work on scientific information extraction relies on entity-relation extraction in narrow domains . current models struggle in domains such as sociology and humanities .
Approach: They propose a multi-domain benchmark for scientific abstract annotations using a unified event extraction schema.
Outcome: The proposed benchmark includes 500 abstracts across five research domains with manual annotations of event segments, triggers, and fine-grained arguments.
Revisiting the Markov Property for Machine Translation (2024.findings-eacl)

Copied to clipboard

Challenge: Statistical machine translation (SMT) has employed Markov models, but autoregressive models are less effective.
Approach: They propose to use a Markov Autoregressive Transformer to model neural machine translation using four WMT benchmarks.
Outcome: The proposed model performs better than autoregressive models on four WMT benchmarks.
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Radiology report generation aims at generating descriptive text from radiology images automatically.
Approach: They propose a weakly supervised contrastive loss method that generates descriptive text from radiology images automatically.
Outcome: The proposed method outperforms previous work on correctness and text generation metrics for two public benchmarks.
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Copied to clipboard

Challenge: Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach: They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome: The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Recent studies have incorporated approaches to improving the standard cross-entropy loss to ameliorate the effect of multimodality.
Approach: They propose a new training oaxe loss which removes the penalty of word order errors in the standard cross-entropy loss.
Outcome: Extensive experiments on NAT benchmarks show that the proposed approach improves translation quality and improves model performance.
Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Federated domain-specific instruction tuning (FedDIT) for large language models (LLMs) aims to enhance performance in specialized domains using distributed private and limited data.
Approach: They introduce an algorithm that explicitly maximizes cross-client domain coverage through diversity-oriented client center selection and retrieval-based augmentation.
Outcome: The proposed algorithm achieves performance gains of 29.19% and domain coverage improvements of 4.82%-21.36% over 11 baselines.
Shallow-to-Deep Training for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that deep training is 1:4 faster than training from scratch.
Approach: They propose a shallow-to-deep training method that learns deep models by stacking shallow models.
Outcome: The proposed method is 1:4 faster than training from scratch and achieves BLEU scores of 30:33 and 43:29 on two translation tasks.
Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation (2025.coling-main)

Copied to clipboard

Challenge: Current named entity recognition methods struggle with text-image mismatch problem due to a lack of visual context.
Approach: They propose an adaptive mixup image augmentation method that generates augmented images based on matching score between text and image .
Outcome: The proposed method can be integrated into existing models and demonstrate consistent performance improvements.
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments (2026.findings-acl)

Copied to clipboard

Challenge: Currently, there are no efficient reinforcement learning (RL) frameworks specifically designed for tool use.
Approach: They propose an automated environment construction pipeline that incorporates scenario decomposition, document generation, function integration, complexity scaling, and localized deployment to enable high-quality training environments without external tools.
Outcome: The proposed framework significantly improves the models’ tool-use performance without degrading their general capabilities.
Knowledge Fusion By Evolving Weights of Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Experimental results on mainstream language models show that Evolver outperforms previous state-of-the-art models by large margins due to the high training costs of large language models.
Approach: They propose a method to integrate multiple models from diverse training scenarios into a unified model.
Outcome: The proposed method outperforms state-of-the-art models on mainstream language models by large margins.
QG-SMS: Enhancing Test Item Analysis via Student Modeling and Simulation (2025.acl-long)

Copied to clipboard

Challenge: Question Generation (QG) tasks are often evaluated using reference-based metrics such as ROUGE and BLEU.
Approach: They propose a QG evaluation framework that leverages Large Language Model for Student Modeling and Simulation to perform test item analysis.
Outcome: The proposed framework improves the QG task and human-simulated student profiles.

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