Papers by Ruoyu Li

19 papers
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing large language model (LLM) agents are unable to adapt to changing domain knowledge and rules.
Approach: They propose an LLM agent framework that continuously learns updated domain knowledge at test time.
Outcome: The proposed agent improves on a customer due diligence name screening task on . the agent learns updated domain knowledge at test time.
LLMaAA: Making Large Language Models as Active Annotators (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing supervised learning methods in natural language processing require large amounts of data.
Approach: They propose an active learning loop that takes LLMs as annotators and puts them into an active loop to determine what to annotate efficiently.
Outcome: The proposed model outperforms existing models with few-shot performance in two NLP tasks.
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing fine-tuning and continual learning methods compress visual representations and emphasize task alignment over visual retention.
Approach: They propose a modality-decoupled gradient descent (MDGD) that regulates gradient updates to preserve effective rank of visual features and explicitly disentangles visual learning from task-specific alignment.
Outcome: The proposed model reduces visual forgetting and improves visual retention . it disentangles visual learning from task-specific alignment and preserves effective rank .
TED-EL: A Corpus for Speech Entity Linking (2024.lrec-main)

Copied to clipboard

Challenge: Current entity linking tasks rely on textual information, but entities usually exist in textual, audio, and visual contexts in real-world data such as social media and video websites.
Approach: They propose a speech entity linking task to recognize mentions from speech and link them to entities in knowledge bases.
Outcome: The proposed model outperforms the existing models on the TED-EL dataset, scoring an F1 score of 60.68%.
Automatic Poetry Generation with Mutual Reinforcement Learning (D18-1)

Copied to clipboard

Challenge: Existing models for automatic poetry generation are based on maximum likelihood estimation (MLE) MLE-based models tend to remember common patterns of the poetry corpus, which results in loss-evaluation mismatch.
Approach: They propose to model the criteria and use them as explicit rewards to guide gradient update by reinforcement learning to motivate the model to pursue higher scores.
Outcome: The proposed model outperforms the current state-of-the-art model and improves on Chinese poetry.
Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods for knowledge base question answering lack causality modeling . previous work fails to model such causalities in their pipeline .
Approach: They propose a causal-enhanced table-filler to overcome sequence-modelling issues . they propose an efficient beam-search algorithm to scale complex queries on large-scale KBs.
Outcome: Experiments on LC-QuAD 1.0 show that the proposed method surpasses state-of-the-arts by a large margin while remaining time and space efficient.
GAVEL: Evidence-Contract Debate with Mechanized Scrutiny for Provenance-Grounded Fact-Checking (2026.findings-acl)

Copied to clipboard

Challenge: Evidence-grounded fact-checking requires predicting claim veracity while returning faithful evidence at fine granularity.
Approach: They propose a multi-agent debate framework that enforces evidence grounding throughout inference.
Outcome: The proposed framework improves provenance-aware metrics over existing frameworks.
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality (2025.emnlp-main)

Copied to clipboard

Challenge: Privacy-sensitive users require deploying large language models within their own infrastructure (on-premises) vulnerabilities in local environments can lead to unauthorized access and potential model theft.
Approach: They propose a framework that secures a few bottom layers in a secure environment . they propose metric to optimize trade-off between protection and customization flexibility .
Outcome: The proposed framework outperforms baselines on five models with 1.3B to 70B parameters.
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Copied to clipboard

Challenge: In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach: They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome: The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.
Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization (2024.findings-emnlp)

Copied to clipboard

Challenge: Prompt optimization is an important technique for adapting Large Language Models (LLMs) to specific tasks.
Approach: They propose a zeroth-order approach which enables efficient prompt tuning solely via inference APIs.
Outcome: The proposed approach outperforms existing black-box prompt tuning methods in terms of performance and convergence speed.
A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction (2023.acl-long)

Copied to clipboard

Challenge: Existing document-level relation extraction methods assume entities and their mentions are given beforehand, which is inadequate for real-world applications.
Approach: They propose a table-to-graph generation model for joint extraction of entities and relations at document-level.
Outcome: The proposed model surpasses existing methods by a large margin and achieves state-of-the-art results on a document-level relation extraction dataset.
AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Copied to clipboard

Challenge: Significant concerns emerge when addressing cultural sensitivity and local values.
Approach: They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome: The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.
Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System (P19-3)

Copied to clipboard

Challenge: Existing systems for automatic poetry generation are model-oriented, resulting in poor user participation.
Approach: They propose a human-machine collaborative Chinese classical poetry generation system called Jiuge . Jiuge allows users to revise unsatisfied parts of a generated poem draft repeatedly .
Outcome: The proposed system allows users to revise unsatisfied parts of a generated poem draft repeatedly.
AtTGen: Attribute Tree Generation for Real-World Attribute Joint Extraction (2023.acl-long)

Copied to clipboard

Challenge: Attribute extraction aims to identify attribute names and the corresponding attribute values from descriptive texts.
Approach: They propose a unified formulation for real-world attribute extraction application, where closed-world, open-world and semi-open attribute extraction tasks are modeled uniformly.
Outcome: The proposed model outperforms existing methods on three datasets and outperformed existing methods by a large margin.
Denoising based Sequence-to-Sequence Pre-training for Text Generation (D19-1)

Copied to clipboard

Challenge: PoDA pre-trains encoders and decoders by denoising noise-corrupted text . Unlike encoder-only or decode-only methods, it can be used for text generation tasks without using any task-specific techniques.
Approach: They propose a sequence-to-sequence (seq2sequ) pre-training method PoDA which denoises autoencoders by denoising noise-corrupted text.
Outcome: The proposed method improves model performance over strong baselines without using any task-specific techniques and significantly speed up convergence.
TeachMaster: Generative Teaching via Code (2026.acl-industry)

Copied to clipboard

Challenge: Existing methods for creating video content are limited by high costs and slow update cycles.
Approach: They propose a paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle execution.
Outcome: The proposed framework reduces production costs to 0.3% of traditional course videos and provides a robust solution for scalable education.
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to bypass security defenses of large language models (LLMs) are not effective, but QueryAttack can be jailbroken.
Approach: They propose a framework to examine generalizability of safety alignment by translating malicious queries into structured non-natural query languages.
Outcome: The proposed framework can achieve high attack success rates and jailbreak various defense methods on mainstream LLMs.
Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension (C18-1)

Copied to clipboard

Challenge: Recent studies have shown that cloze-style reading comprehension is a popular task for measuring the progress of natural language understanding.
Approach: They propose a multi-perspective framework which can be seen as joint training of heterogeneous experts and aggregate context information from different perspectives.
Outcome: The proposed framework achieves new state-of-the-art over previous strong baselines on a recently released cloze-test 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