Papers by Xiaofei Li

31 papers
Is Word Segmentation Necessary for Deep Learning of Chinese Representations? (P19-1)

Copied to clipboard

Challenge: Using word-based models, we compare word-oriented models with char-based ones . word-driven models are more vulnerable to data sparsity and the presence of out-of-vocabulary words .
Approach: They benchmark word-based models with char-based model which does not involve word segmentation in four NLP benchmark tasks.
Outcome: The proposed model outperforms char-based models in four NLP benchmark tasks.
Dependency Parsing as MRC-based Span-Span Prediction (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for dependency parsing address the issue that edges should be constructed at the text span/subtree level rather than word level.
Approach: They propose a method that constructs dependency trees by directly modeling span-span relations by modeling subtree-subtree relationships.
Outcome: The proposed method constructs dependency trees by modeling span-span relations . it can retrieve missing spans in the span proposal stage, which leads to higher recall .
Multi-target Backdoor Attacks for Code Pre-trained Models (2023.acl-long)

Copied to clipboard

Challenge: Existing work for backdoor attacks on neural code models insert triggers into task-specific data for code-related downstream tasks, limiting the scope of attacks.
Approach: They propose task-agnostic backdoor attacks for code pre-trained models . they use two learning strategies to implant backdoors into code understanding and generation models - Poisoned Seq2Seq learning and token representation learning .
Outcome: The proposed model is pre-trained with two learning strategies to support the multi-target attack of downstream code understanding and generation tasks.
Red Teaming Language Models for Processing Contradictory Dialogues (2024.emnlp-main)

Copied to clipboard

Challenge: a recent study shows that language models are prone to self-contradiction during dialogues.
Approach: They propose a red teaming framework that detects and attempts to explain dialogues, then modifies existing contradictory content using the explanation.
Outcome: The proposed task improves the ability to detect contradictory dialogues and provides valid explanations.
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference (2026.acl-long)

Copied to clipboard

Challenge: Existing static compression methods suffer from coarse-grained caching and high I/O overhead.
Approach: They propose a training-free dynamic compression framework that uses a sparse attention mechanism to categorize attention heads based on stability and similarity.
Outcome: The proposed framework achieves state-of-the-art performance on long-context benchmarks and accelerates decoding by up to 3 compared to the original model with a 224K context.
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.
Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models face persistent challenges when handling long-context tasks . existing methods that reduce input have the risk of discarding key information .
Approach: To address this issue, we propose a multi-agent reasoning framework called Tree of Agents . the framework segments input into chunks processed by independent agents .
Outcome: The proposed model outperforms baseline models on long-context tasks.
An MRC Framework for Semantic Role Labeling (2022.coling-1)

Copied to clipboard

Challenge: Existing work on semantic role labels ignores the semantic connection between the two tasks . et al. (2010) defined two types of semantic roles: core roles and non-core roles.
Approach: They propose to use machine reading comprehension to bridge the gap between these two tasks . they formalize predicate disambiguation as multiple-choice machine reading understanding .
Outcome: The proposed framework achieves state-of-the-art or comparable results to previous work . it uses the descriptions of candidate senses of a given predicate as options to select the correct sense .
Explainable Quantum Program Repair with Verifiable Proof Traces (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to program repair provide only post-hoc, non-verifiable explanations that are not executable or verifiably.
Approach: They propose a framework that couples repair generation with machine-checkable executable explanations for quantum programs where correctness hinges on subtle semantic properties such as circuit equivalence and fidelity preservation.
Outcome: Experiments on QASMBench with mutation-generated quantum program bugs show that the proposed framework improves both semantic precision and explanation faithfulness over baselines that rely on unconstrained or purely natural-language explanations.
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection (2021.emnlp-main)

Copied to clipboard

Challenge: Existing studies studying OOD detection in NLP often rely on external data to diversify model predictions.
Approach: They propose a framework which mimics OOD detection behavior without external data . they take text classification as an archetype and compare them to existing datasets .
Outcome: The proposed framework can resolve in- and out-distribution examples in a natural way using existing datasets.
Fast Nearest Neighbor Machine Translation (2022.findings-acl)

Copied to clipboard

Challenge: Fast kNN-MT uses the entire corpus as the datastore for the nearest neighbor search . knn-MT is two-orders slower than vanilla MT models .
Approach: They propose a fast kNN-MT model that uses the entire corpus as the datastore for nearest neighbor search.
Outcome: The proposed model is two-orders faster than kNN-MT and is only two times slower than the standard model.
Audio-Aware Large Language Models as Judges for Speaking Styles (2025.findings-emnlp)

Copied to clipboard

Challenge: Audio-aware large language models (ALLMs) can understand textual and non-textual information in the audio input.
Approach: They use audio-aware large language models (ALLMs) to evaluate the speaking styles of SLMs on two tasks: voice style instruction following and role-playing.
Outcome: The proposed models can understand the textual and non-textual information in the audio input and can be used as a judge to assess the speaking styles of SLMs.
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.
Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for learning representations of structured knowledge are limited to the minority of people with technical skills.
Approach: They propose a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem.
Outcome: The proposed model improves on two SQL tasks and shows a 1.7 and 2.2 percentage point improvement over existing methods.
What to Fuse and How to Fuse: Exploring Emotion and Personality Fusion Strategies for Explainable Mental Disorder Detection (2023.findings-acl)

Copied to clipboard

Challenge: Mental health disorders (MHD) are one of the greatest challenges facing our healthcare systems and modern societies in general.
Approach: They integrate and extend the research by conducting extensive experiments with three types of deep learning-based fusion strategies: feature-level fusion, model fusion and task fusion.
Outcome: The proposed techniques show that they can be used to improve mental health detection from textual data.
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.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
Paraphrase Generation as Unsupervised Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for paraphrase generation rely on labeled datasets or are limited in narrow domains.
Approach: They propose a paradigm for paraphrase generation by treating the task as unsupervised machine translation based on pairs of unlabeled monolingual sentences.
Outcome: The proposed paradigm can generate paraphrases on a large unlabeled monolingual corpus without relying on bilingual sentence pairs.
BertGCN: Transductive Text Classification by Combining GNN and BERT (2021.findings-acl)

Copied to clipboard

Challenge: Text classification is a core task in natural language processing (NLP) Graph neural networks (GNNs) serve as an effective approach for transductive learning.
Approach: They propose a model that combines large scale pretraining and transductive learning for text classification.
Outcome: The proposed model achieves SOTA performance on a wide range of datasets.
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.
Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing testing methods are system-level and provide limited insight into which capability deficiencies cause task failures.
Approach: They propose a capability-oriented testing approach that enables failure detection and attribution by seed selection and mutation.
Outcome: The proposed method detects more failure cases and pinpoints capability-level deficiencies than state-of-the-art baselines, providing more interpretable and actionable guidance for improving embodied agents.
GPT-NER: Named Entity Recognition via Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Large-scale language models (LLMs) have shown impressive ability for in-context learning with limited training data.
Approach: They propose a novel sequence labeling task that transforms a sequence labeled as a text-generation task into a self-verification task that LLMs can adapt to.
Outcome: The proposed model performs better on NER than supervised models on a variety of tasks . the proposed model can be easily adapted by LLMs to generate a text sequence .
ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)

Copied to clipboard

Challenge: Existing studies show that causal language models lack expressiveness due to poor discrimination ability.
Approach: They propose a contrastive learning framework that enhances discrimination of representations and bridges the gap with encoder-only models.
Outcome: The proposed framework improves discrimination and source code generation capabilities on a variety of downstream tasks.
Layer-wise Model Pruning based on Mutual Information (2021.emnlp-main)

Copied to clipboard

Challenge: In spite of impressive results of neural networks, the huge model size has hindered their applications in cases where computation and memory resources are limited.
Approach: They propose a method for layer-wise pruning using mutual information based feature selection in SVMs and logistic regression.
Outcome: The proposed pruning strategy offers greater speedup and higher performance than weight-based pruning methods.
Sentence Similarity Based on Contexts (2022.tacl-1)

Copied to clipboard

Challenge: Existing methods to measure sentence similarity face limited dataset size and training-test gap . existing methods lack large-scale labeled datasets with labeles that are labor-intensive and expensive .
Approach: They propose a framework that measures sentence similarity by comparing probabilities of generating two sentences given the same context.
Outcome: The proposed framework achieves significant performance boosts over baselines under supervised and unsupervised settings.
Do Code Semantics Help? A Comprehensive Study on Execution Trace-Based Information for Code Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Code Large Language Models have limited ability to reason about runtime behavior and understand functionality . authors present a generic framework to support integrating semantic information to code task-relevant prompts .
Approach: a study examines the role of trace-based semantic information in boosting supervised fine-tuning and post-phase inference of Code LLMs.
Outcome: a new framework integrates semantic information to code task-relevant prompts . the proposed framework shows that trace-based semantic information boosts reasoning ability .
Text Classification via Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Large-scale Language Models (LLMs) have shown the ability for in-context learning.
Approach: They propose a progressive reasoning strategy tailored to addressing complex linguistic phenomena such as intensification, contrast, irony and limited number of tokens allowed in in-context learning.
Outcome: The proposed model performs better on 4 out of 5 widely-used text-classification benchmarks, while demonstrating comparable performance to SOTA on MR.
Dice Loss for Data-imbalanced NLP Tasks (2020.acl-main)

Copied to clipboard

Challenge: Using dice loss, we find that data imbalance is a common issue in many NLP tasks . data imbalance affects the performance of many tasks, such as tagging and machine reading comprehension .
Approach: They propose to use dice loss to replace the standard cross-entropy objective for data-imbalanced NLP tasks.
Outcome: The proposed training objective achieves significant performance boost on a wide range of data imbalanced tasks.
Shanks: Simultaneous Hearing and Thinking for Spoken Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing large language models and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn.
Approach: They propose a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to user input.
Outcome: The proposed framework enhances real-time user–SLM interaction in two scenarios.
Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries (2022.coling-1)

Copied to clipboard

Challenge: Existing models focus on local word prediction, and cannot make high level plans on what to generate.
Approach: They propose a pipelined system that summarises, outlines and elaborates on each bullet point to generate the corresponding segment.
Outcome: The proposed system produces long texts with significantly better quality and faster convergence speed.
Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion Knowledge (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for stance detection are struggling to cope with the data across targets.
Approach: They propose a model that uses external knowledge as a bridge to enable knowledge transfer across different targets.
Outcome: The proposed model outperforms existing methods on a large real-world dataset.

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