Papers by Yuqing Li

23 papers
Multilingual Speech Translation from Efficient Finetuning of Pretrained Models (2021.acl-long)

Copied to clipboard

Challenge: Recent advances in text pretraining and finetuning have improved multitasking applications significantly.
Approach: They propose a minimalistic LNA finetuning approach to build multilingual speech-to-text translation using a pretrained speech encoder and text decoder.
Outcome: The proposed approach surpasses the cascaded ST benchmark for 36 translation directions on the large-scale multilingual ST benchmark CoVoST 2.
An Empirical Study of Position Bias in Modern Information Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: a new evaluation framework is used to assess the extent and impact of position bias in information retrieval.
Approach: They introduce a position-aware retrieval benchmark and a diagnostic metric to quantify position bias . they compare models with BM25, dense embedding models, ColBERT-style late-interaction models .
Outcome: The proposed framework evaluates retrieval models for position bias from a worst-case perspective.
A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure (2020.acl-main)

Copied to clipboard

Challenge: Text-level discourse parsing of discourse rhetorical structure (DRS) is a fundamental research topic in natural language processing.
Approach: They propose a top-down neural architecture for text-level discourse parsing . they cast the parser as a recursive split point ranking task .
Outcome: The proposed top-down approach is more suitable for text-level discourse parsing.
Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden.
Approach: They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations.
Outcome: The proposed system improves time-to-target by 2.17-8.48 on real-world datasets.
AC-EVAL: Evaluating Ancient Chinese Language Understanding in Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: AC-EVAL is a benchmark designed to assess the advanced knowledge and reasoning capabilities of LLMs within the context of ancient Chinese.
Approach: They propose a benchmark to assess the advanced knowledge and reasoning capabilities of LLMs in ancient Chinese.
Outcome: AC-EVAL aims to assess the comprehension of ancient Chinese texts . the benchmark covers 13 tasks covering historical facts, geography, social customs, art, philosophy, classical poetry and prose.
Rectified Sparse Attention for Efficient Long-Sequence Generation (2026.findings-acl)

Copied to clipboard

Challenge: Recent sparse decoding methods improve efficiency but suffer from KV cache misalignment, resulting in performance degradation.
Approach: They propose a method that combines block-sparse attention with periodic dense rectification to bound error accumulation and preserve alignment with the pretraining distribution.
Outcome: Experiments on math reasoning, language modeling, and retrieval tasks show that ReSA achieves near-lossless generation quality with significantly improved efficiency.
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel (2025.findings-acl)

Copied to clipboard

Challenge: Long-context language models exhibit position bias, also known as "lost in the middle" research shows that even long-contemporary LLMs fail to utilize all context information effectively .
Approach: They propose a method to mitigate position bias by scaling positional hidden states . they propose to use a channel of hidden states to modify positional Hidden states a LCLM's positional bias .
Outcome: The proposed method can improve performance by 15.2% in a "lost in the middle" benchmark.
A Multi-Modal Knowledge Graph for Classical Chinese Poetry (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing studies in classical Chinese poetry area focus on generation and analysis of poetry.
Approach: They propose to integrate the visual information of words in classical Chinese poetry into a multi-modal knowledge graph.
Outcome: The proposed model bridges the semantic gap between two modalities and achieves state-of-the-art performance on the poetry-image retrieval task.
Multilingual Translation from Denoising Pre-Training (2021.findings-acl)

Copied to clipboard

Challenge: Recent work shows potential of training one model for multilingual machine translation . but little has been explored on the potential to combine denoising pretraining with multilingual translation in a single model.
Approach: They propose to combine denoising pretraining with multilingual machine translation in a single model.
Outcome: The proposed model improves over models trained from scratch and bilingually for translation into English.
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach: They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome: The proposed method achieves a superior balance between downstream learning and general capability retention.
PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case Study (2024.emnlp-main)

Copied to clipboard

Challenge: philology requires years of professional training in extensive knowledge memorization and manual textual retrieval.
Approach: They curated the PhiloCorpus-ZH, a rich collec-tion of ancient Chinese texts spanning a millennium with 30 diverse topics, including firsthand folk copies.
Outcome: The PhiloCorpus-ZH corpus facilitated the development of the first LLM tailored for discovering ancient Chinese manuscripts.
MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks (2024.eacl-long)

Copied to clipboard

Challenge: Existing approaches to automating ML are time-consuming and difficult to understand for human developers.
Approach: They propose a framework that leverages large language models to develop ML solutions for novel tasks.
Outcome: The proposed framework bridges the gap between machine intelligence and human knowledge by exploiting state-of-the-art large language models.
CSL: A Large-scale Chinese Scientific Literature Dataset (2022.coling-1)

Copied to clipboard

Challenge: Existing datasets centered around the English language restrict development of Chinese scientific NLP.
Approach: They present a large-scale Chinese scientific literature dataset based on Chinese papers . they use semi-structured data as a natural annotation for many supervised NLP tasks .
Outcome: The proposed dataset can serve as a Chinese corpus and perform many supervised tasks.
End-to-End Open-Domain Question Answering with BERTserini (N19-4)

Copied to clipboard

Challenge: a new open-domain question answering system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles.
Approach: They propose an end-to-end question answering system that integrates BERT with an IR reader.
Outcome: The proposed system improves on a standard benchmark test collection.
LoRASC: Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing low-rank adaptations have limited expressiveness, a tendency to overfit, and sensitivity to hyperparameter settings.
Approach: They propose a technique to enhance LoRA’s expressiveness and generalization capabilities while preserving its training efficiency.
Outcome: The proposed method outperforms baselines, mitigates overfitting, enhances model stability, and improves OOD robustness.
AMAS: Adaptively Determining Communication Topology for LLM-based Multi-agent System (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models (LLMs) have revolutionized natural language processing, but their practical implementation as autonomous multi-agent systems remains fraught with unresolved challenges.
Approach: They propose a dynamic graph selector that redefines LLM-based MAS by exploiting the intrinsic properties of individual inputs to intelligently direct query trajectories.
Outcome: The proposed framework exceeds state-of-the-art approaches in question answering, mathematical deduction, and code generation benchmarks.
InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering (2025.emnlp-main)

Copied to clipboard

Challenge: Retrieval-Augmented Generation (RAG) frameworks struggle with identifying whether retrieved documents meaningfully contribute to answer generation.
Approach: They propose a document-related metric to quantify the contribution of retrieved documents to correct answer generation.
Outcome: The proposed framework outperforms existing approaches on both single and multiple retrieval paradigms.
Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders (2021.eacl-main)

Copied to clipboard

Challenge: Recent work in multilingual translation has improved translation quality surpassing bilingual baselines using deep transformer models with increased capacity.
Approach: They propose a deep encoder with multiple shallow decoders to reduce inference latency while maintaining translation quality.
Outcome: The proposed model achieves 1.8x speedup on average compared to a standard transformer model with no drop in translation quality.
UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks, but their effectiveness relies on supervised training with extensive labeled data and computational resources.
Approach: They propose an unsupervised method that leverages Internal Probing of Large language models for Code generation without any external corpus, even unlabeled code snippets.
Outcome: The proposed method can achieve competitive performance compared to supervised approaches while reducing the dependency on labeled data and computational resources.
Situated Embedding Models for Context-Aware Dense Retrieval (2026.acl-short)

Copied to clipboard

Challenge: Existing embedding models are not well-equipped to encode situated context effectively, i.e., situating a chunk’s meaning within its context.
Approach: They propose to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.
Outcome: The proposed model outperforms state-of-the-art embedding models on a book-plot retrieval dataset.
Misleading Relation Classifiers by Substituting Words in Texts (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to generate adversarial examples for relation classification are vulnerable to adversarials.
Approach: They propose a method that uses most important parts of speech to substitute words with synonyms or hyponyms to generate adversarial texts of high quality.
Outcome: The proposed method can generate adversarial texts of high quality and most relationships can be correctly identified in the process of human evaluation.
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression (2024.acl-long)

Copied to clipboard

Challenge: Longer prompts introduce irrelevant and redundant information, which can weaken LLMs' performance.
Approach: They propose a prompt compression tool that improves LLMs' perception of key information in input prompts by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo.
Outcome: The proposed solution improves performance and reduces costs and latency by up to 21.4% with around 4x fewer tokens in the NaturalQuestions benchmark.

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