Papers by Qing Sun

19 papers
Enhance Robustness of Language Models against Variation Attack through Graph Integration (2024.lrec-main)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are used in many NLP applications but their vulnerability to adversarial attacks can lead to false or misleading information being distributed.
Approach: They propose a method to incorporate a Chinese character variation graph into pre-trained language models to increase their robustness against character variation attacks in Chinese content.
Outcome: The proposed method outperforms existing language models in combating adversarial attacks in Chinese content.
Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts.
Approach: They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis.
Outcome: The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents.
Unified Structure Generation for Universal Information Extraction (2022.acl-long)

Copied to clipboard

Challenge: Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas.
Approach: They propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources.
Outcome: The proposed framework can model different IE tasks, generate targeted structures, and learn general IE abilities from different knowledge sources.
LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following (2025.coling-main)

Copied to clipboard

Challenge: E-commerce authoring requires engaging, diverse, and targeted content . Large language models lack memorization of domain-specific features in e-commerce applications .
Approach: They propose a unified e-commerce authoring models that address contextual preferences of customers, sellers, and platforms . they propose to integrate interleaved features presented by participating objects into the models to empower authoring applications with comprehensive scenario understanding .
Outcome: The proposed models achieve state-of-the-art evaluation performance and exhibit the advantage in zero-shot practical applications.
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach: They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome: The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.
Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) struggle when it comes to specialized domains due to limited domain-specific knowledge.
Approach: They propose an adaptive method that automatically identifies valuable words from a given domain vocabulary.
Outcome: The proposed method has been validated on three Chinese datasets and performed on general tasks.
Few-shot Named Entity Recognition with Self-describing Networks (2022.acl-long)

Copied to clipboard

Challenge: Existing few-shot named entity recognition (NER) models capture information from limited instances while transferring useful knowledge from external resources.
Approach: They propose a self-describing mechanism for few-shot NER which can universally describe mentions using concepts and automatically map novel entity types to concepts.
Outcome: The proposed model can universally describe mentions using concepts and automatically map novel entity types to concepts and adaptively recognize entities on-demand.
ConRPG: Paraphrase Generation using Contexts as Regularizer (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods for paraphrase generation lack reliable supervision signals.
Approach: They propose an unsupervised paradigm for paraphrase generation based on contextual language models, candidate filtering and paraphrase model training based upon the selected candidates.
Outcome: The proposed paradigm outperforms existing paraphrase generation methods in supervised and unsupervised setups.
Learning to Revise References for Faithful Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that noisy reference summaries can be detrimental to model performance.
Approach: They propose to selectively re-write unsupported reference sentences to better reflect source data.
Outcome: The proposed method improves reference quality while retaining all data.
An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-training large language models is a standard practice in the natural language processing community.
Approach: They propose to use elastic weight consolidation to mitigate catastrophic forgetting when pre-trained large language models are evaluated on generic benchmarks.
Outcome: The proposed model achieves state-of-the-art on out-of domain tasks with minimal pre-training . elastic weight consolidation provides best overall scores yielding only a 0.33% drop in performance across seven generic tasks while remaining competitive in bio-medical tasks.
More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs (2024.emnlp-main)

Copied to clipboard

Challenge: a recent study shows that performance on general tasks decreases after Large Language Models are fine-tuned on domain-specific tasks.
Approach: They propose a general capability integration approach to integrate general capabilities and domain knowledge within a single instance.
Outcome: The proposed method improves performance on domain-specific tasks by integrating general capabilities and domain knowledge.
AMR-TST: Abstract Meaning Representation-based Text Style Transfer (2023.findings-acl)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) is a semantic representation that can enhance natural language generation (NLG) by providing a logical semantic input.
Approach: They propose an AMR-based text style transfer technique that converts source text to an AML graph and generates transferred text based on the AMR graph modified by a TST policy named style rewriting.
Outcome: The proposed method achieves state-of-the-art results compared with baseline models in automatic and human evaluations.
Exploring Continual Learning for Code Generation Models (2023.acl-short)

Copied to clipboard

Challenge: Large-scale code generation models such as Copilot and CodeT5 are expensive to train and re-train.
Approach: They propose a benchmark for Continual Learning (CL) that covers a wide range of tasks with different input and output programming languages.
Outcome: The proposed method improves on Prompt Pooling with Teacher Forcing, which suffers catastrophic forgetting due to stark distribution shifts in coding tasks.
Neural Entity Recognition with Gazetteer based Fusion (2021.findings-acl)

Copied to clipboard

Challenge: Named entity recognition systems can be applied to clinical domains where only limited data is accessible and interpretability is important.
Approach: They propose to use auxiliary gazetteer model to fuse it with NER system . this allows for better robustness and interpretability across different clinical datasets .
Outcome: The proposed model is data efficient and can adapt to new mentions in gazetteers without retraining.
ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information (2021.acl-long)

Copied to clipboard

Challenge: ChineseBERT model incorporates glyph and pinyin information of Chinese characters into pretraining . proposed model achieves new performance boost over baseline models with fewer training steps .
Approach: They propose a ChineseBERT model that incorporates glyph and pinyin information into pretraining . the glyph embedding is obtained based on different fonts of a character, and the pinyink embeddment characterizes the pronunciation of Chinese characters.
Outcome: The proposed model achieves new performance boosts over baseline models with fewer training steps.
Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies aim to integrate multiple sub-tasks into a unified ABSA model but suffer from major disadvantages .
Approach: They propose a multi-task learning approach to make use of sub-tasks for a unified ABSA.
Outcome: The proposed model can work well when some sub-tasks are absent, and the interactive relations among subtasks not adequate.
FoldMoE: Efficient Long Sequence MoE Training via Attention-MoE Pipelining (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to training LLMs with Mixture-of-Experts (MoE) architecture on long sequences are limited by the insufficient computation.
Approach: They propose a MoE training system that enables token-level overlapping across entire Transformer blocks through novel attention-MoE pipelining.
Outcome: The proposed system achieves 1.49x and 2.72x speedup over state-of-the-art token-level overlapping and non-overlapping baselines on GPT-MoE models with sequences up to 32K tokens.
Fine-grained Entity Typing via Label Reasoning (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to fine-grained entity typing are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-granular entities.
Approach: They propose a label reasoning network that exploits label dependencies knowledge entailed in the data.
Outcome: The proposed network can model, learn and reason complex labels in a sequence-to-set, end-to end manner.
Planning-Aware Code Infilling via Horizon-Length Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Current approaches to fill-in-the-middle (FIM) often fail to generate content that aligns well with the surrounding context.
Approach: They propose a training objective that teaches models to predict the number of remaining middle tokens at each step.
Outcome: The proposed training objective improves FIM performance by up to 24% on diverse benchmarks across file-level and repository-level.

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