Papers by Yunlong Xu

32 papers
Continual Learning with Semi-supervised Contrastive Distillation for Incremental Neural Machine Translation (2024.acl-long)

Copied to clipboard

Challenge: Multi-domain learning is a good solution for solving domain tasks but it requires retraining when adding a new domain.
Approach: They propose to exploit unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.
Outcome: The proposed framework exploits unlabeled data from the same distributions of the older domains to avoid catastrophic forgetting.
Towards Making the Most of Dialogue Characteristics for Neural Chat Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Neural Chat Translation (NCT) models that use dialogue characteristics of chat are often incoherent and speakerirrelevant.
Approach: They propose to introduce the modeling of dialogue characteristics into the NCT model by capturing the inherent dialogue characteristics.
Outcome: The proposed model can translate conversational text between speakers of different languages.
Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation (2023.acl-long)

Copied to clipboard

Challenge: Existing knowledge distillation techniques for neural machine translation lack special treatment on the top-1 information, which is limiting the potential of KD.
Approach: They propose a method to distill knowledge from top-1 predictions of teachers and a technique to infuse more additional knowledge by distilling on the data without ground-truth targets.
Outcome: The proposed method outperforms the vanilla word-level KD and outperfies the existing methods on three different students with different capacity gaps.
A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis (D19-1)

Copied to clipboard

Challenge: Existing models use aspect-independent encoders for sentence representation generation.
Approach: They propose an aspect-guided deep transition model which guides the sentence encoding from scratch with a specially-designed deep transition architecture.
Outcome: The proposed model outperforms existing models on multiple datasets on aspect-category sentiment analysis and aspectterm sentiment analysis without additional features.
A Variational Hierarchical Model for Neural Cross-Lingual Summarization (2022.acl-long)

Copied to clipboard

Challenge: Existing studies on cross-lingual summarization focus on pipeline methods or jointly training an end-to-end model through an auxiliary MT or MS objective.
Approach: They propose a hierarchical model for the cross-lingual summarization task . the model is based on the conditional variational auto-encoder .
Outcome: The proposed model generates better cross-lingual summaries than comparison models in the few-shot setting.
D2TV: Dual Knowledge Distillation and Target-oriented Vision Modeling for Many-to-Many Multimodal Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies focus on improving MMS models by filtering summary-unrelated visual features with implicit learning or explicitly complex training objectives.
Approach: They propose a multimodal multimodal summarization task that aims to generate summaries in any language with document inputs in any languages and the corresponding image sequence.
Outcome: The proposed task can generate summaries in any language with document inputs in any languages and the corresponding image sequence.
kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in task-oriented parsing involve formulating the task as a sequence-to-sequence problem, relying on a wealth of labeled data.
Approach: They propose a task-oriented parsing framework that integrates nearest-neighbor learning with a nearest-nearest approach.
Outcome: The proposed model can be used to synthesize computer programs based on a natural-language prompt without additional data or specialized prompts.
A Two-Stage Framework with Self-Supervised Distillation for Cross-Domain Text Classification (2024.lrec-main)

Copied to clipboard

Challenge: Existing work on cross-domain text classification relies on domain-invariant features or task-agnostic features.
Approach: They propose a two-stage framework for cross-domain text classification that leverages or reuses rich labeled data from the source domain and unlabeled data in the target domain.
Outcome: The proposed framework achieves state-of-the-art on a public cross-domain text classification benchmark.
MSCTD: A Multimodal Sentiment Chat Translation Dataset (2022.acl-long)

Copied to clipboard

Challenge: Multimodal machine translation and textual chat translation have received considerable attention . however, little research has been devoted to multimodal machine translator in conversations .
Approach: They propose a task to generate more accurate translations with the help of dialogue history and visual context.
Outcome: The proposed task can generate more accurate translations with the help of dialogue history and visual context.
Cross-Lingual Knowledge Editing in Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Knowledge editing is a promising technique to adapt large language models to new knowledge without retraining from scratch.
Approach: They propose to use a multilingual dataset to translate a large-scale cross-lingual synthetic dataset from English to Chinese and then to evaluate their performance in Chinese.
Outcome: The proposed method can change model performance on several special cases without retraining from scratch.
A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to generate high-quality speech with limited target speaker corpus require extensive training data.
Approach: They propose an auxiliary corpus compression algorithm that reduces the training cost while the naturalness of synthesized speech is not significantly degraded.
Outcome: The proposed method significantly reduces training costs while maintaining the naturalness of synthesized speech.
Modeling Bilingual Conversational Characteristics for Neural Chat Translation (2021.acl-long)

Copied to clipboard

Challenge: Neural chat translation aims to translate bilingual conversational text due to its inherent characteristics such as role preference, dialogue coherence, and translation consistency.
Approach: They propose to model the translation quality of conversational text by learning distributions of bilingual conversational characteristics.
Outcome: The proposed approach outperforms baseline models and is widely available.
OpenSLU: A Unified, Modularized, and Extensible Toolkit for Spoken Language Understanding (2023.acl-demo)

Copied to clipboard

Challenge: Spoken Language Understanding (SLU) is a task-oriented dialogue system . open-source toolkit provides a unified, modularized, and extensible toolkit for SLU .
Approach: They introduce an open-source toolkit to provide a unified toolkit for spoken language understanding.
Outcome: The proposed toolkit unifies 10 models for both single-intent and multi-intention scenarios.
Beyond Static Evaluation: A Dynamic Approach to Assessing AI Assistants’ API Invocation Capabilities (2024.lrec-main)

Copied to clipboard

Challenge: Existing evaluation methods for human-machine interactions are static and can be misleading.
Approach: They propose to use a LLM-based user agent to assess an assistant's API call capability without human involvement.
Outcome: The proposed method mirrors real human conversation patterns in human-machine interactions, and shows that it aligns more closely with human assessment.
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Copied to clipboard

Challenge: Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach: They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome: The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.
CM-Align: Consistency-based Multilingual Alignment for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Current large language models (LLMs) show a significant performance gap in alignment between English and other languages.
Approach: They propose a consistency-based method to construct high-quality multilingual preference data for improving multilingual alignment.
Outcome: The proposed method is based on three LLMs and three common tasks and shows that it performs better than current methods.
Concise and Precise Context Compression for Tool-Using Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods suffer from key information loss and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Approach: They propose two strategies for compressing tool documentation into concise and precise summary sequences for tool-using language models.
Outcome: The proposed approach achieves comparable performance to the upper-bound baseline under 16x compression ratio.
Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for few-shot text classification often encounter problems drawing accurate class prototypes from support set samples.
Approach: They propose a meta-learning method that leverages the information within the task itself . they propose Query-Data-Augmenter and Label-Adapter to build a task-adaptive metric space .
Outcome: The proposed method shows obvious advantages over state-of-the-art models on eight benchmark datasets.
Multilingual Knowledge Editing with Language-Agnostic Factual Neurons (2025.coling-main)

Copied to clipboard

Challenge: Existing methods to update factual knowledge overlook connections of same knowledge between different languages, resulting in knowledge conflicts and limited edit performance.
Approach: They propose a method to edit multilingual knowledge simultaneously that avoids knowledge conflicts and improves edit performance.
Outcome: The proposed method avoids knowledge conflicts and improves edit performance on bi-ZsRE and MzsRE benchmarks.
A Quality-based Syntactic Template Retriever for Syntactically-Controlled Paraphrase Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing syntactically-controlled paraphrase generation models perform well with human-annotated or well-chosen syntaktic templates.
Approach: They propose a quality-based Syntactic Template Retriever to retrieve templates based on the quality of the to-be-generated paraphrases.
Outcome: The proposed algorithm can generate high-quality paraphrases without sacrificing quality.
Can Large Language Models Understand You Better? An MBTI Personality Detection Dataset Aligned with Population Traits (2025.coling-main)

Copied to clipboard

Challenge: Existing data on MBTI personality detection are based on self-reported labels and fail to capture the full range of population personality traits.
Approach: They construct a manually annotated MBTI personality detection dataset with soft labels under the guidance of psychologists and use them to identify the task.
Outcome: The MBTIBench is the first manually annotated MBti personality detection dataset with soft labels under the guidance of psychologists.
Self-Constructed Context Decompilation with Fined-grained Alignment Enhancement (2024.findings-emnlp)

Copied to clipboard

Challenge: Decompilation is the process of converting compiled code back into a high-level programming language for analysis when source code is unavailable.
Approach: They propose two methods to improve decompilation performance without fine-tuning and fine-grained alignment enhancement to achieve further improvements.
Outcome: The proposed methods achieved a Re-Executability performance improvement of approximately 3.90% on the Decompile-Eval benchmark, establishing a new state-of-the-art performance of 52.41%.
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Current Large Reasoning Models exhibit two critical limitations when processing non-English languages: (1) They struggle to maintain input-output language consistency; (2) They generally perform poorly with wrong reasoning paths and lower answer accuracy compared to English.
Approach: They propose a language-consistency reward and a cross-lingual thinking alignment reward to improve the model's interpretability and accuracy.
Outcome: The proposed model achieves nearly 100% language consistency and superior performance on two multilingual benchmarks (MMATH and PolyMath).
Improving Language Model Reasoning with Self-motivated Learning (2024.lrec-main)

Copied to clipboard

Challenge: Large-scale high-quality training data is important for improving the performance of models.
Approach: They propose a framework that motivates the model to automatically generate rationales on existing datasets and improves the performance of reasoning through reinforcement learning.
Outcome: The proposed model outperforms InstructGPT on multiple reasoning datasets and outperformed InstructGPT on other datasets.
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.
ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing evaluation methods for large language models are labor-intensive and lack efficiency.
Approach: They propose a framework dedicated to assessing long-text generation that includes in-depth human-curated meta-questions spanning various domains . they use a set of proxy-quests with pre-annotated answers to assess the content's quality by incorporating the generated texts as contextual background.
Outcome: The proposed framework assesses the quality of long-text content by matching it with references through human evaluation or automated metrics.
Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization (2023.acl-long)

Copied to clipboard

Challenge: Existing studies on multimodal abstractive summarization focus on how to use extracted visual features to produce a concise summary given the multimodal data.
Approach: They propose to improve the visual quality of the multimodal abstractive summarization model by capturing summary-oriented visual features.
Outcome: The proposed approach achieves state-of-the-art under 44 languages and is highly effective on high-resource English datasets.
Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-Experts (2025.acl-long)

Copied to clipboard

Challenge: Existing large language models (LLMs) have remarkable ability in high-resource languages, but their performance in multilingual scenarios is still limited.
Approach: They propose a layer-wise expert allocation algorithm to determine the appropriate number of new experts for each layer.
Outcome: The proposed method outperforms the previous state-of-the-art baseline with 60% fewer experts in the single-expansion setting and 33.3% fewer in the lifelong-expanding setting.
An Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to Aspect-based sentiment analysis do not exploit the interactive relations among subtasks and do not utilize document-level labeled domain/sentiment knowledge, which restricts their performance.
Approach: They propose an iterative multi-knowledge transfer network for end-to-end ABSA that leverages the inter-task interaction between subtasks.
Outcome: The proposed approach improves on three benchmark datasets.
Understanding Translationese in Cross-Lingual Summarization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing datasets involve translation, but translationese is distinguished from original text . previous studies have shown that translationeses in CLS are not a problem in training sets .
Approach: They propose to use cross-lingual summarization to generate a concise summary in a target language from a document in . existing datasets typically involve translation in their creation, but the translated text is distinguished from the original written in that language.
Outcome: The proposed method systematically investigates how translationese affects CLS model evaluation and performance when it appears in source documents or target summaries.
Scheduled Multi-task Learning for Neural Chat Translation (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to improve chat translation focus on modeling bilingual dialogue characteristics . however, there is insufficient data and simple joint training methods .
Approach: They propose a scheduled multi-task learning framework to incorporate large-scale chat translation data into training by adding a second pre-training stage between the original pre- training and fine-tuning stages.
Outcome: The proposed framework improves translation tasks on four language directions.
RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-training (2023.findings-acl)

Copied to clipboard

Challenge: Existing V&L pre-training methods rely on strictly-aligned multilingual image-text pairs generated from English-centric datasets.
Approach: They propose a regularized cross-lingual visual contrastive learning objective that constrains representation proximity of weakly-aligned multilingual image-text pairs.
Outcome: The proposed model outperforms competing models with weak zero-shot capability on 5 multi-modal tasks across 6 languages.

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