Papers by Jie Cao

33 papers
Soft Language Clustering for Multilingual Model Pre-training (2023.acl-long)

Copied to clipboard

Challenge: Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from the source language or when pre-training data is limited in size.
Approach: They propose a method that contextually retrieves prompts as flexible guidance for encoding instances conditionally.
Outcome: The proposed method improves on the XTREME task and also for low-resource languages in unsupervised sentence retrieval.
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Copied to clipboard

Challenge: a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach: They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome: The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.
Learning In-context Learning for Named Entity Recognition (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to recognize entities in text are limited by the diversity of entity types and the lack of high-quality annotations.
Approach: They propose an in-context learning-based NER approach that can inject in-const NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances.
Outcome: The proposed method outperforms the PLMs+fine-tuning counterparts on 4 few-shot NER datasets and significantly outperformed the Plms+initialized extractors.
FlowRAG: Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for Graph-based retrieval-augmented generation rely on implicit semantic relevance propagation.
Approach: They propose a semantic-aware retrieval framework that improves both semantic recall and explicit reasoning.
Outcome: Extensive experiments show that FlowRAG improves both semantic recall and explicit reasoning.
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding (2022.findings-acl)

Copied to clipboard

Challenge: Unsupervised contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data.
Approach: They propose a momentum contrastive learning model with negative sample queue for sentence embedding with a simulated model with EMA update mechanism.
Outcome: The proposed model achieves a Spearman’s correlation of 77.27% on the semantic text similarity task and a maximum traceable distance metric.
Mind the Gap between the Application Track and the Real World (2023.acl-short)

Copied to clipboard

Challenge: Recent advances in NLP have led to a rise in inter-disciplinary and application-oriented research.
Approach: They examine the relationship between motivations described in NLP papers and models and evaluations which comprise the proposed solution.
Outcome: The proposed solution improves educational dialog understanding system when used in a realistic classroom environment.
Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation (P19-1)

Copied to clipboard

Challenge: Rhetoric is a vital element in modern Chinese poetry, and plays an essential role in improving its aesthetics. however, to date, it has not been considered in research on automatic poetry generation.
Approach: They propose a rhetorically controlled encoder-decoder for modern Chinese poetry generation . their model captures various rhetorical patterns in an encoder and incorporates mixtures .
Outcome: The proposed model outperforms state-of-the-art methods in terms of fluency, coherence, meaningfulness, and rhetorical aesthetics.
CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging (2026.findings-acl)

Copied to clipboard

Challenge: Existing PEFT methods suffer from limited parameter efficiency and coarse-grained adaptation due to proliferation of LoRA experts and instance-level routing.
Approach: They propose a new MoE-LoRA framework that incorporates expert diversity, parameter efficiency, and fine-grained adaptation.
Outcome: The proposed framework outperforms existing methods on multiple tasks while maintaining parameter efficiency.
An Augmented Benchmark Dataset for Geometric Question Answering through Dual Parallel Text Encoding (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for solving geometric problems are limited due to lack of high-quality datasets and efficient neural solvers.
Approach: They propose to annotate 2,518 geometric problems with richer types and greater difficulty using a benchmark dataset.
Outcome: The proposed method improves the accuracy of automatic geometric problem solving to 66.09%.
ℛ3: Advertisement Compliance ℛectification via Group-ℛelative Experience Extractor and Curriculum ℛeinforcement (2026.acl-industry)

Copied to clipboard

Challenge: Existing methods of content moderation are infeasible due to over-editing and compromise the advertiser’s original semantic intent.
Approach: They propose a framework to harmonize compliance with original intent preservation that integrates a data-driven framework and a curriculum to enforce compliance while maximizing semantic consistency.
Outcome: The proposed framework outperforms state-of-the-art baselines on industrial datasets and on online A/B testing on industrial video.
Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to improve the reasoning performance of large language models rely on intuitive instance-level feedback, which limits the reasoning capabilities.
Approach: They propose a framework that pushes LLMs toward System-2-like critic capability by using a step-wise CoT reasoning paradigm and automatic construction of weak-supervision data without human annotation.
Outcome: The proposed model significantly improves task-solving performance by filtering out invalid solutions or iterative refinement.
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks on longcontext large language models fail to reflect their deep understanding capabilities across diverse tasks.
Approach: They propose a benchmark to assess the ability of long-context large language models to handle long-text problems.
Outcome: The proposed model achieves 50.1% accuracy when directly answering the questions . human experts achieve only 53.7% accuracy under a 15-minute time constraint .
MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for parameter-efficient fine-tuning (PEFT) are limited by computational costs and performance degradation.
Approach: They propose a method that integrates Low-Rank Adaptation and Mixture-of-Experts (MoE) they propose combining expert load imbalance and representation collapse to improve LLM performance .
Outcome: The proposed method outperforms homogeneous MoE-LoRA architectures in performance and parameter efficiency.
TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understanding (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing text-rich image understanding benchmarks lack scale and fragmented scenarios . a new full-image structured output format is proposed to enable fine-grained evaluation of perception and reasoning capabilities.
Approach: They propose a large-scale, multilingual benchmark that includes over 100,000 annotations and 22,000 question-answer pairs.
Outcome: The proposed framework provides a comprehensive platform for developing and evaluating next-generation multimodal AI systems.
Visual Prompt Tuning for Few-Shot Text Classification (2022.coling-1)

Copied to clipboard

Challenge: Existing work on pretraining models for text classification uses image encoders instead of visual prompts.
Approach: They propose a method to deploy large-scale pre-trained models in the prompt-tuning paradigm in few-shot learning.
Outcome: The proposed method outperforms the most recent prompt-tuning methods on five public text classification datasets.
Translation via Annotation: A Computational Study of Translating Classical Chinese into Japanese (2026.eacl-long)

Copied to clipboard

Challenge: Ancient people translated classical Chinese into Japanese using a system of annotations placed around characters.
Approach: They propose to introduce an LLM-based annotation pipeline and construct a dataset from digitized open-source translation data to improve sequence tagging tasks.
Outcome: The proposed method achieves high scores on direct machine translation, but could serve as a supplement to LLMs to improve the quality of character’s annotation.
Enhancing Talk Moves Analysis in Mathematics Tutoring through Classroom Teaching Discourse (2025.coling-main)

Copied to clipboard

Challenge: a recent study focuses on analyzing tutoring discourse using talk moves . scaling the collection, annotation, and analysis of extensive tutoring dialogues is a challenge .
Approach: They propose to analyze tutoring discourse using talk moves to develop machine learning models . they use a compact dataset to analyze dialogue context, speaker information and ablation data .
Outcome: The proposed model improves performance in classrooms and in small groups . the proposed model is based on existing datasets and models designed for classroom teaching .
A Comparative Study on Schema-Guided Dialogue State Tracking (2021.naacl-main)

Copied to clipboard

Challenge: Recent work proposes using natural language descriptions to define domain ontologies for dialog state tracking.
Approach: They propose to use natural language descriptions to define domain ontologies instead of tag names for each intent or slot . they introduce a set of newly designed bench-marking descriptions and show model robustness .
Outcome: The proposed model is robust on homogeneous and heterogeneously described descriptions in training and evaluation.
DeepGen: Diverse Search Ad Generation and Real-Time Customization (2022.emnlp-demos)

Copied to clipboard

Challenge: Existing systems that generate ads manually are not effective in generating ad copy and generating millions of ads for large businesses.
Approach: They propose a system that generates fluent ads from advertiser’s web pages in an abstractive fashion and solves practical issues such as factuality and inference speed.
Outcome: The proposed system generates fluent ads from advertiser’s web pages in an abstractive fashion and solves practical issues such as factuality and inference speed.
Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that biased samples can be brittle for VQA models . however, the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data.
Approach: They propose a contrastive learning approach that exploits biased samples for unbiased information that contributes to reasoning.
Outcome: The proposed method achieves competitive performance on the OOD dataset while maintaining robustness on the ID dataset.
An Empirical Study of Many-to-Many Summarization with Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that large language models (LLMs) have strong multilingual abilities, giving them the potential to perform M2MS in real applications.
Approach: They propose to use many-to-many summarization (M2MS) to generate a brief summary in any language given a document also in any other language.
Outcome: The proposed model outperforms zero-shot LLMs in terms of automatic evaluations.
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models (2025.findings-naacl)

Copied to clipboard

Challenge: Text-to-image (T2I) models can be used to generate harmful content such as sexually explicit, unfaithful, and misleading or Not-Safe-for-Work (NSFW) images.
Approach: They propose a more practical and universal attack that does not require the presence of a target model.
Outcome: The proposed attack bypasses both text and image safety checkers while preserving high semantic alignment with the target prompt.
Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach (2022.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models capture factual knowledge from massive texts . but they are still quite behind the SOTA KGC models in terms of performance .
Approach: They propose to use open-world assumption to evaluate PLM-based knowledge graph completion models . they propose to convert each triple and its support information into natural prompt sentences .
Outcome: The proposed model is more accurate under the open-world assumption (OWA) this setting manual checks the correctness of knowledge that is not in KGs.
Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training (2022.naacl-main)

Copied to clipboard

Challenge: Recent studies show pre-trained language models contain matching subnetworks that have similar transfer learning performance as the original PLM.
Approach: They propose to prune matching subnetworks using magnitude-based pruning . they propose to optimize the subnetwork structure towards the pre-training objectives .
Outcome: The proposed method is more efficient in searching subnetworks and advantageous when fine-tuning within a range of data scarcity.
OTSeq2Set: An Optimal Transport Enhanced Sequence-to-Set Model for Extreme Multi-label Text Classification (2022.emnlp-main)

Copied to clipboard

Challenge: Extreme multi-label text classification (XMTC) is a task of finding the most relevant subset labels from an extremely large label set.
Approach: They propose an autoregressive sequence-to-set model for XMTC tasks named OTSeq2Set.
Outcome: The proposed model outperforms other competitive baselines on 4 benchmark datasets.
Simulating Classroom Education with LLM-Empowered Agents (2025.naacl-long)

Copied to clipboard

Challenge: Initial studies have focused on task-specific, independent LLM-empowered agents, but the potential of LLMs within a multi-agent collaborative framework for classroom simulation with real user participation remains unexplored.
Approach: They propose a multi-agent classroom simulation teaching framework that recognizes representative class roles and introduces a novel class control mechanism for automatic classroom teaching.
Outcome: The proposed framework can simulate dynamic learning environment for users with active teacher-student and student-studente interactions.
Do LLMs Encode Frame Semantics? Evidence from Frame Identification (2025.emnlp-main)

Copied to clipboard

Challenge: Using the FrameNet lexical resource, we evaluate large language models under prompt-based inference and observe that they can perform frame identification effectively even without explicit supervision.
Approach: They evaluate large language models under prompt-based inference and observe that they encode latent knowledge of frame semantics.
Outcome: The proposed model can generate coherent frame definitions while generalizing well to out-of-domain benchmarks.
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes (P19-1)

Copied to clipboard

Challenge: a new study examines the role of dialogue observers in psychotherapy . the model is based on motivational interviewing, which is effective for treating addictions .
Approach: They propose to model MI behavioral codes for therapists by an observer . they propose to use the observer to forecast therapist and client MI behavioral code .
Outcome: The proposed model outperforms baseline models for both tasks and reveals tradeoffs in performance.
Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL (2025.emnlp-main)

Copied to clipboard

Challenge: Existing Text-to-SQL research focuses on specific database systems, limiting adaptability to different dialects.
Approach: They propose a framework that employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap.
Outcome: The proposed framework outperforms existing methods that generate SQL queries directly.
SSR-A: Spatial- and Semantic-Aware Instructions and Curriculum Reinforcement for Advertisement Compliant Rectification (2026.acl-industry)

Copied to clipboard

Challenge: Existing methods to fix non-compliant images suffer from over-editing, destroying original intent and perceptual similarity.
Approach: They propose a framework for the minimalist rectification of non-compliant image ads.
Outcome: The proposed framework outperforms state-of-the-art baselines in both compliance and preservation of visual and commercial consistency.
Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA (2022.findings-emnlp)

Copied to clipboard

Challenge: Visual Question Answering (VQA) models are prone to learn the shortcut solution formed by dataset biases rather than the intended solution.
Approach: They propose a dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Outcome: The proposed dataset considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Evolutionary Negative Module Pruning for Better LoRA Merging (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for integrating multiple low-rank Adaptation experts into a single backbone are limited by negative modules.
Approach: They propose a plug-and-play LoRA pruning method to locate and exclude negative modules prior to merging.
Outcome: The proposed method boosts the performance of existing merging algorithms across languages and vision domains.
Re3: Relevance & Recency Retrieval for Mitigating Temporal Hallucination (2026.acl-long)

Copied to clipboard

Challenge: Existing retrievers suffer from temporal-semantic misalignment and outdated-document interference . Existing frameworks suffer from both temporal validity and outdated factual versions .
Approach: They propose a framework that mitigates temporal hallucinations by embedding heterogeneous temporal signals into the semantic space to ensure retrieval fidelity.
Outcome: Experiments show that Re3 outperforms baselines by 9.7% in generation accuracy . the framework outperformed strongest baselines on challenging dynamic tasks .

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