Papers by Xin Dai

23 papers
DSP: Discriminative Soft Prompts for Zero-Shot Entity and Relation Extraction (2023.findings-acl)

Copied to clipboard

Challenge: Prompt-based methods have shown their efficacy in transferring general knowledge within pre-trained language models (PLMs) however, when applied to zero-shot entity and relation extraction, they struggle with the limited coverage of verbalizers to labels and the slow inference speed.
Approach: They propose a method which reformulates zero-shot tasks into token discrimination tasks without having to construct verbalizers.
Outcome: The proposed method outperforms baselines on two zero-shot entity recognition datasets with higher inference speed and achieves 7.5% improvement over previous state-of-the-art models on Wiki-ZSL and FewRel.
Scaling Laws for Code: Every Programming Language Matters (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on language-agnostic settings, neglecting the inherently multilingual nature of modern software development.
Approach: They propose a proportion-dependent scaling law that prioritizes high-utility languages . they propose PLs to have varying effects during pre-training that affect model performance .
Outcome: The proposed scaling law is based on 1000+ experiments across multiple languages and models.
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks (2026.acl-long)

Copied to clipboard

Challenge: Existing supervised defense methods rely on labeled malicious agents to train a supervised model of malicious behavior.
Approach: They propose an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.
Outcome: The proposed method detects diverse attack types across MAS with various communication patterns while maintaining superior generalizability compared to baselines.
mCLIP: Multilingual CLIP via Cross-lingual Transfer (2023.acl-long)

Copied to clipboard

Challenge: Existing multilingual vision-language pretrained models are biased towards English due to the lack of sufficient non-English image-text pairs.
Approach: They propose to train a retrieval-efficient dual-stream multilingual VLP model by aligning CLIP model and a multilingual text encoder through a novel Triangle Cross-modal Knowledge Distillation method.
Outcome: Empirical results show that mCLIP achieves new state-of-the-art performance for both zero-shot and finetuned multilingual image-text retrieval tasks.
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval (2024.emnlp-industry)

Copied to clipboard

Challenge: Existing models for text retrieval are based on a multi-stage process that involves retrieving documents from a large corpus.
Approach: They propose to build a multilingual text representation model and a cross-encoder reranker from scratch for text retrieval.
Outcome: The proposed models outperform the state-of-the-art models on long-context retrieval benchmarks.
Mitigate Extrinsic Social Bias in Pre-trained Language Models via Continuous Prompts Adjustment (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods of extrinsic bias mitigation rely on manual word lists for sensitive groups . however, these word lists are limited by length and scope, resulting in poor performance.
Approach: They propose a method which generates continuous token lists from the entire vocabulary space and uses them to bridge the gap between outputs and targets in fairness learning process.
Outcome: The proposed method outperforms baseline methods on three NLU tasks.
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling (2024.acl-long)

Copied to clipboard

Challenge: Existing language models that use discrete representations for unified processing of various modalities are limited to text generation and do not include multimodal output.
Approach: They propose a multimodal language model that utilizes discrete representations for unified processing of various modalities.
Outcome: The proposed model can be trained stably without any alterations to existing models or training paradigms.
Revealing the Attention Floating Mechanism in Masked Diffusion Models (2026.findings-acl)

Copied to clipboard

Challenge: Masked diffusion models (MDMs) leverage bidirectional attention and a denoising process.
Approach: They investigate the attention behaviors of Masked diffusion models by revealing the phenomenon of Attention Floating.
Outcome: The proposed model doubles the performance of autoregressive models in knowledge-intensive tasks.
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making (2021.acl-long)

Copied to clipboard

Challenge: Entity Matching (EM) aims at recognizing entity records that denote the same real-world object.
Approach: They propose a novel EM framework that consists of Heterogeneous Information Fusion and Key Attribute Tree Induction to decouple feature representation from matching decision.
Outcome: The proposed framework outperforms SOTA EM models on 6 public datasets and 3 industrial datasets.
A Lifelong Multilingual Multi-granularity Semantic Alignment Approach via Maximum Co-occurrence Probability (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to mask and predict tokens in multilingual text limit multilingual interaction .
Approach: They propose a lifelong multilingual multi-granularity semantic alignment approach which continuously extracts massive aligned linguistic units from noisy data via a maximum co-occurrence probability algorithm.
Outcome: The proposed approach improves translation performance on WMT14 18 benchmarks in twelve directions.
A Chinese Corpus for Fine-grained Entity Typing (2020.lrec-1)

Copied to clipboard

Challenge: Existing datasets for fine-grained entity typing are limited to English . a corpus of 4,800 mentions is manually labeled with free-form entity types .
Approach: They propose a Chinese fine-grained entity typing task that uses crowdsourcing . they categorize each mention into 10 general types and use a large tag set to predict open set of types .
Outcome: The proposed dataset contains 4,800 mentions manually labeled in Chinese . it also categorizes all the fine-grained types into 10 general types .
Demystifying Data Organization for Enhanced LLM Training (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have revolutionized various fields, yet their training efficiency is heavily reliant on effective data curation.
Approach: They propose to reuse pre-computed sample-level scores originally generated for data efficiency and introduce two new data ordering methods to improve LLM training.
Outcome: The proposed methods improve the stability and performance of LLM training.
Improving Fine-grained Entity Typing with Entity Linking (D19-1)

Copied to clipboard

Challenge: Existing methods for fine-grained entity typing require a large tag set and knowledge of the context.
Approach: They propose a deep neural model that uses context and information from entity linking to improve fine-grained entity typing.
Outcome: The proposed model achieves 5% absolute strict accuracy improvement over the state of the art on two datasets.
Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability (2021.emnlp-main)

Copied to clipboard

Challenge: Existing models for multi-hop reasoning are not able to evaluate their interpretability . a recent study found that many paths are unreasonable .
Approach: They propose a framework to evaluate the interpretability of multi-hop reasoning models . they annotate all possible rules and establish a benchmark .
Outcome: The proposed framework outperforms existing models in terms of performance and interpretability.
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption.
Approach: They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.
Outcome: Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.
Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation (2022.findings-acl)

Copied to clipboard

Challenge: Recent large-scale vision-language pre-training models are powerful in multimodal classification and retrieval tasks.
Approach: They propose to augment a vision-language pre-training model with a textual pre-trained language model . the model achieves 44.5% zero-shot accuracy on multimodal generation tasks .
Outcome: The proposed model achieves 44.5% zero-shot accuracy on open-ended visual question answering and image captioning tasks.
SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for multi-hop knowledge graph reasoning suffer from slow and poor convergence . a transformer model can be used to learn and predict in an end-to-end fashion, giving faster convergence compared to previous methods .
Approach: They propose a Sequence-to-sequence based multi-hop reasoning framework . it uses an encoder-decoder transformer structure to translate the query to a path .
Outcome: The proposed framework can learn and predict in an end-to-end fashion, which gives better and faster convergence.
On Domain-Adaptive Post-Training for Multimodal Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Adapting general multimodal large language models to specific domains is important for practical applications.
Approach: They investigate domain adaptation of multimodal large language models via post-training . they develop a generate-then-filter pipeline that curates diverse visual instruction tasks .
Outcome: The proposed model outperforms existing models in domain adaptation by combining data from open-source models with training pipelines.
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive.
Approach: They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory .
Outcome: The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient.
SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach: They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome: The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.
Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for generating and curating high-quality instruction-tuning data rely heavily on the quality of seed data or strong assumptions about the structure and content of web documents.
Approach: They propose a fully automated framework for synthesizing high-quality instruction-tuning (IT) data directly from raw web documents with minimal assumptions.
Outcome: The proposed framework outperforms state-of-the-art baselines by 16.65% across four instruction-following benchmarks.
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems (2025.emnlp-main)

Copied to clipboard

Challenge: Empirical studies for communication topology design often overlook why and when sparse and dense topologies help or hinder collaboration.
Approach: They propose a topology design approach that balances error suppression and beneficial information propagation by fusing connectivity patterns from dense and sparse graphs.
Outcome: The proposed topology design achieves superior performance across tasks with sparse and dense graphs.
Towards Text-Image Interleaved Retrieval (2025.acl-long)

Copied to clipboard

Challenge: Existing multimodal information retrieval models rely on single-image inputs . current models use a dense retrieval paradigm, but this approach is not effective .
Approach: They propose a text-image interleaved retrieval task where query and document are interleaves . they adapt off-the-shelf retrievers and build a dense baseline by interleaded multimodal large language model .
Outcome: The proposed model achieves significant improvements over the baseline by substantially fewer visual tokens.

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