Papers by Yixuan Li

27 papers
Non-Autoregressive Text Generation with Pre-trained Language Models (2021.eacl-main)

Copied to clipboard

Challenge: Autoregressive generation models generate tokens in a left-to-right, token-by-token fashion, resulting in lag in inference.
Approach: They propose to use BERT as the backbone of a non-autoregressive generation model for greatly improved performance.
Outcome: The proposed model outperforms existing non-autoregressive models and achieves competitive performance with many strong autoregressive model.
A Survey of LLM-based Agents in Medicine: How far are we from Baymax? (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks.
Approach: They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement.
Outcome: The findings highlight the future directions in medical reasoning, physical system integration, and training simulations.
HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to zero-shot Dialog State Tracking (zs-DST) are inadequate to generalize to new domains without extensive training.
Approach: They propose a framework that enhances zero-shot slot inference through robust prompt alignment.
Outcome: Experiments on multi-domain datasets show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST.
ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws (2024.emnlp-main)

Copied to clipboard

Challenge: Existing quality filtering methods rely on a high-quality dataset as reference . Existing methods introduce potential biases and compromise diversity .
Approach: They propose a method that evaluates text quality based on the perplexity difference between two language models trained on the same data.
Outcome: The proposed approach improves performance of pre-trained models without increasing training costs.
MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: achieving synergistic improvements between generalization and domain specialization remains a challenge in pre-training and post-training.
Approach: They propose a test-time cross-domain knowledge integration method that integrates general-purpose and domain-specific models to enhance their performance on complex, domainspecific tasks.
Outcome: The proposed method combines the outputs of general-purpose and domain-specific models to improve their performance on complex, domainspecific tasks.
Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for data annotation use an aggressive approach prompting LLMs to determine a single gold label for each unlabeled sample.
Approach: They propose a teacher-student framework that distills candidate annotations with a Small Language Model (SLM) they propose to use LLMs to generate and distill candidate annotation with slms to ensure unique labels are provided for downstream tasks.
Outcome: The proposed method outperforms existing methods due to uncertainty in LLMs and is noisetolerant.
500xCompressor: Generalized Prompt Compression for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Prompt compression is important for large language models to increase inference speed, reduce computation cost, and improve user experience.
Approach: They propose a method that compresses natural language contexts into a special token . they propose to reduce computations and memory costs by reducing the complexity .
Outcome: The proposed method reduces computations and memory costs by 27-90% . it retains 70-74% and 77-84% of the LLM capabilities at high compression ratios .
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to enhance multilingual reasoning capabilities rely on costly multilingual training or employ prompting with external translation tools.
Approach: They propose a training-free inference-time method to enhance multilingual reasoning capabilities via Representation Engineering without additional training data or tools.
Outcome: The proposed method outperforms existing methods on four reasoning benchmarks in English and Thai and Swahili.
Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Prior work focused on data preprocessing, focusing on filtering and cleaning data . a study aimed to improve fine-grained scheduling of data order in epochs .
Approach: They propose a fine-grained scheduling method of data order in epochs to fill this gap . they define data difficulty based on relevance between data and model .
Outcome: The proposed method improves on pre-training and small-scale fine-tuning experiments 2.4% over baselines.
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have catalyzed the rise of reasoningintensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers.
Approach: They propose a large-small LLM collaboration framework that synergizes large and small language models to achieve high-quality reasoning with significantly reduced computational cost.
Outcome: The proposed framework outperforms the mentor LLM while preserving the benefits of the thinking paradigm of LLMs.
CMMLU: Measuring massive multitask language understanding in Chinese (2024.findings-acl)

Copied to clipboard

Challenge: Existing large language models struggle to achieve an accuracy of even 60%, which is the pass mark for Chinese exams.
Approach: They propose to use CMMLU to evaluate Chinese multilingual and Chinese LLMs in a comprehensive benchmark that covers various subjects and settings.
Outcome: The proposed benchmark covers natural sciences, social sciences, engineering, and the humanities and aims to improve on existing models.
MedConQA: Medical Conversational Question Answering System based on Knowledge Graphs (2022.emnlp-demos)

Copied to clipboard

Challenge: Existing medical dialogue systems have the problems of weak scalability, insufficient knowledge, and poor controllability.
Approach: They propose a medical conversational question-answering system based on the knowledge graph to improve scalability and controllability.
Outcome: The proposed system can conduct knowledge-grounded dialogues with users, using a Chinese medical knowledge graph and a large-scale dataset.
Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly used as rerankers, but their ranking behavior can be steered by small, natural-sounding prompts.
Approach: They propose a token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings.
Outcome: The proposed method outperforms state-of-the-art base-lines and is hard to detect.
Joint Annotation of Morphology and Syntax in Dependency Treebanks (2024.lrec-main)

Copied to clipboard

Challenge: Syntactic treebanks have been in development since the 1970s . they are now available for a vast array of languages from across the globe .
Approach: They propose new formats to annotate syntactic and morphological relations in a dependency treebank using distributional criteria for the choice of the head of any combination.
Outcome: The proposed formats are compatible with the UD schema for syntactic treebanks.
NAT: Enhancing Agent Tuning with Negative Samples (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning and reinforcement learning use only positive examples, limiting their efficiency in low-resource scenarios.
Approach: They propose a method that leverages both successful and failed trajectories for fine-tuning, maximizing the utility of limited resources.
Outcome: The proposed method surpasses existing methods, including SFT, DPO, and PPO, across various tasks.
Audio-centric Video Understanding Benchmark without Text Shortcut (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in multimodal large language models (MLLMs) focus on visual abilities, but audio is essential for video understanding.
Approach: They propose an audio-centric video understanding benchmark to evaluate video comprehension capabilities of multimodal LLMs with a particular focus on auditory information.
Outcome: The proposed video understanding benchmarks evaluate video comprehension capabilities of multimodal models with a particular focus on auditory information.
Prompt Compression for Large Language Models: A Survey (2025.naacl-long)

Copied to clipboard

Challenge: Current methods for improving LLM efficiency focus on optimizing the model itself, while prompt-centric methods focus on lowering the complexity of input.
Approach: They propose to use prompt compression to optimize the compression encoder and combine hard and soft prompt methods to improve the efficiency of LLMs.
Outcome: The proposed methods are categorized into hard prompt methods and soft prompt methods.
AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Copied to clipboard

Challenge: Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach: They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome: The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.
Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking (2022.acl-long)

Copied to clipboard

Challenge: Experimental results show that task-oriented dialogue systems have attracted growing attention and achieved substantial progress.
Approach: They propose a method that dynamically selects relevant dialogue contents for each slot . they retrieve turn-level utterances and evaluate their relevance to the slot from three perspectives .
Outcome: The proposed method achieves state-of-the-art performance on MultiWOZ 2.1 and MultiWOz 2.2 and superior performance on multiple mainstream benchmark datasets.
Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection (2023.acl-long)

Copied to clipboard

Challenge: Out-of-distribution (OOD) detection is critical for reliable predictions over text . fine-tuning with pre-trained language models has been a de facto procedure .
Approach: They propose to leverage pre-trained language models for OOD detection without fine-tuning on ID data.
Outcome: The proposed approach outperforms the fine-tuned model under distributional shifts.
A Critical Analysis of Document Out-of-Distribution Detection (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing document understanding models focus on single-modal inputs such as images or texts.
Approach: They propose to use a spatial-aware adapter to adapt transformer-based language models to document domain to exploit multi-modal information.
Outcome: The proposed model significantly improves the OOD detection performance compared to using a standard language model and to competitive baselines.
HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing grammar generation models perform sub-optimally, resulting in inconsistent syntactic and semantic accuracy.
Approach: They propose an LLM-driven hybrid genetic algorithm to optimize grammar generation by inferring grammars from a set of examples and generated in Backus-Naur Form.
Outcome: The proposed algorithm improves syntactic and semantic accuracy of generated grammars across LLMs.
Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal Models (2025.acl-long)

Copied to clipboard

Challenge: Multiple-choice question answering (MCQA) is widely used to assess the understanding capability of Large Multimodal Models (LMMs).
Approach: They propose a task to evaluate the robust understanding capability of Large Multimodal Models (LMMs) they introduce a benchmark to assess performance across various ability dimensions .
Outcome: The proposed model can withhold answers when encountering unsolvable problems of MCQA, proving it understands the answer.
Large Language Models are Better Reasoners with Self-Verification (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to solve complex natural language processing tasks require multiple steps to verify the answers.
Approach: They propose to use chain of thought prompting to solve reasoning tasks with large language models.
Outcome: The proposed method can improve reasoning performance on arithmetic, commonsense, and logical reasoning datasets.
Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA (2026.findings-acl)

Copied to clipboard

Challenge: Existing multi-document QA benchmarks require information from only a few documents with limited cross-document reasoning.
Approach: They propose a benchmark for multi-document analytical QA that extracts and synthesizes information across multiple documents to perform quantitative analysis.
Outcome: The proposed approach improves both process and outcome metrics but still has bottlenecks compared to human experts.
Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuning (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive capabilities but face significant challenges from hallucinations, which arise from insufficient knowledge or context.
Approach: They propose a novel two-stage approach for contextual question answering that enhances LLMs’ ability to recognise their knowledge boundaries while the second reinforces instruction adherence through carefully designed causal prompts.
Outcome: The proposed approach significantly reduces incorrect answers in contextual QA and improves models’ faithfulness to parametric knowledge, mitigating hallucinations in general QA tasks.
Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation (2024.acl-long)

Copied to clipboard

Challenge: Fine-grained vision-language models (VLMs) have been widely used for inter-modality local alignment between fixed patches and textual words, but they provide incomplete representations of lesions.
Approach: They propose an Adaptive patch-word Matching model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explicit explanations.
Outcome: The proposed model correlates chest X-ray image regions with words in medical reports and provides explanations for the generation process.

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