Papers by Haoyu Xu

23 papers
ToolGrad: Efficient Tool-use Dataset Generation with Textual “Gradients” (2026.findings-acl)

Copied to clipboard

Challenge: Prior work synthesizes tool-use LLM datasets by first generating a user query, then complex tool-using annotations like DFS.
Approach: They propose an agentic framework that synthesizes user queries and generates valid tool-use chains . they propose a dataset with more complex tool use, lower cost, and almost 100% pass rate .
Outcome: Experiments show that tools trained on ToolGrad outperform expensive baseline datasets and proprietary LLMs.
TC–RAG: Turing–Complete RAG’s Case study on Medical LLM Systems (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to RAG neglect system state variables, resulting in poor performance and erroneous knowledge accumulation.
Approach: They propose a framework that incorporates a Turing Complete System to manage state variables and manage retrieval halting.
Outcome: The proposed framework improves on seven real-world healthcare datasets and shows that it is more accurate than existing methods.
Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers (P19-1)

Copied to clipboard

Challenge: Existing approaches to extract multiple relations from a paragraph require multiple passes over the paragraph.
Approach: They propose a method to extract multiple relations from a paragraph by encoding the paragraph only once.
Outcome: The proposed approach can perform state-of-the-art on the benchmark ACE 2005.
Unleashing the Power of Language Models in Text-Attributed Graph (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on graph learning on text-attributed graphs have been limited by memory cost and underutilization of relationships between nodes and words.
Approach: They propose a Node Representation Update Pre-training Architecture based on Co-modeling text and graph to learn representations of papers and words simultaneously.
Outcome: The proposed model outperforms baselines on the ogbn-arxiv benchmark dataset.
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Despite advances in training Large Language Models, they remain vulnerable to jailbreak, an adversarial attack method.
Approach: They propose an adversarial jailbreak algorithm that exploits the gradient information of the suffix tokens to accelerate the optimization process.
Outcome: The proposed model achieves 1.5x speedup while maintaining high attack success rates.
RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive performance but face high computational costs and latency, limiting their deployment in resource-constrained settings.
Approach: They propose a robust RAG framework for large language models via Margin-aware Preference Optimization to enhance the accuracy and reliability of SLMs.
Outcome: The proposed framework surpasses state-of-the-art benchmarks on three open-domain question answering tasks.
MMedAgent: Learning to Use Medical Tools with Multi-modal Agent (2024.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal Large Language Models (MLLMs) exhibit limited generality and often fall short when compared to specialized models.
Approach: They propose a multi-modal medical agent that picks the most suitable medical tools based on user inputs.
Outcome: The proposed agent performs better than open-source models and the closed-source model, GPT-4o.
Hierarchy-Aware Global Model for Hierarchical Text Classification (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for hierarchical text classification are limited and lack holistic structural information.
Approach: They propose a hierarchy-aware global model with two variants that learn hierarchy-based label embeddings through an encoder and conduct inductive fusion of label-alike text features.
Outcome: The proposed model improves on three benchmark datasets.
Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation (2026.findings-acl)

Copied to clipboard

Challenge: Autoregressive sequence modeling has been successful in many domains, but maintaining long-term coherence and structural integrity remains a challenge.
Approach: They propose an ACG paradigm that relies on anchor features from previously generated musical content to guide subsequent generation during the autoregressive process.
Outcome: The proposed framework outperforms existing methods in symbolic music generation tasks.
Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for fine-tuning pre-trained language models overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions.
Approach: They propose a low-parameters Prompt Tuning method which leverages prompt decomposition and compressed outer product to facilitate multiple interactions among prompt tokens.
Outcome: Experiments on six architectures and eight datasets show that the proposed method outperforms state-of-the-art methods in performance and efficiency.
Logic Rules as Explanations for Legal Case Retrieval (2024.lrec-main)

Copied to clipboard

Challenge: Recent efforts to learn explainable legal case retrieval models fail to provide faithful and interpretable explanations for legal cases.
Approach: They propose a framework that uses logic rules to explain legal case retrieval results . they extend benchmarks of LeCaRD and ELAM with manually annotated logic rules .
Outcome: The proposed framework is able to provide faithful explanations for legal case retrieval.
Complex Question Decomposition for Semantic Parsing (P19-1)

Copied to clipboard

Challenge: Existing methods that ignore the decompositionality of complex questions are not suitable for complex question semantic parsing.
Approach: They propose a hierarchical semantic parsing method which utilizes the decompositionality of complex questions for semantic paring.
Outcome: The proposed method improves on a large scale complex question semantic parsing dataset.
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing large language models (LLMs) have achieved some success, but their knowledge understanding and memory capacity significantly degrades after extensive editing.
Approach: They propose a method that stores the basis vectors of the representation space of past edits in a knowledge cache and projects the gradient of the current edit onto a space orthogonal to previous knowledge for updating.
Outcome: The proposed method improves question-answering ability and hallucination mitigation by 14% and 61% for large language models after 3,000 edits.
AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction (2026.acl-long)

Copied to clipboard

Challenge: Currently, knowledge graphs are decoupled from their downstream application, resulting in suboptimal graph structures.
Approach: They propose a framework to directly optimize KG construction for task performance using Reinforcement Learning (RL).
Outcome: The proposed framework improves performance across multiple QA benchmarks and consistently achieves significant performance gains over task-agnostic baseline graphs.
Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers (2025.emnlp-main)

Copied to clipboard

Challenge: Autoregressive language models excel in text-to-audio generation, but lag behind diffusion models by a non-trivial margin.
Approach: They propose a framework that integrates multiple isolated transformers with causal conditioning and anti-causal alignment via reinforcement learning.
Outcome: The proposed framework outperforms existing LM-based and diffusion-based systems in audio synthesis.
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)

Copied to clipboard

Challenge: Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English.
Approach: They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries.
Outcome: The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation.
Enhancing SQL Table Acquisition with Reverse Engineering for Text-to-SQL (2025.findings-emnlp)

Copied to clipboard

Challenge: Text-to-SQL oriented table acquisition suffers from heterogeneous semantic gap.
Approach: They propose a Reverse Engineering based table acquisition approach that reversely generates potentially-matched questions conditioned on table schemas instead of forward table search using queries.
Outcome: The proposed approach achieves competitive performance on two benchmarks, including SpiderUnion and BirdUnion.
OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment (2026.acl-long)

Copied to clipboard

Challenge: Existing reward models rely on scalar or pairwise judgments that fail to capture multifaceted nature of human preferences.
Approach: They propose a rubric-based reward model that uses a large collection of prompt, rubric pairs to generate a scalar score or preference label for each response.
Outcome: The proposed model surpasses strong size-matched baselines by 8.4% across multiple benchmarks.
RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation (2026.findings-acl)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) enhances large language models by integrating external knowledge retrieved at inference time.
Approach: They evaluate RAG systems using MassiveDS, a large-scale datastore with mixture of knowledge.
Outcome: The proposed approach improves performance on knowledge-intensive NLP tasks.
Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation (2024.lrec-main)

Copied to clipboard

Challenge: Existing acceleration methods for text generation ignore the importance of the distribution of sampling steps, resulting in slow sampling rates.
Approach: They propose a technique to accelerate diffusion models for text generation without additional training by using a Bayesian optimization approach.
Outcome: The proposed technique achieves 400x acceleration even with minimal sampling steps after down to less than 1 minute of optimization yielding a competitive performance even with minimum sampling steps.
Effective In-Context Example Selection through Data Compression (2024.findings-acl)

Copied to clipboard

Challenge: In-context learning has been validated in large language models, but the mechanism and selection strategy for in-cont example selection lacks systematic and in-depth research.
Approach: They propose a data compression approach to select in-context examples using large language models.
Outcome: The proposed method shows a significant improvement of 5.90% across five real-world datasets using four language models.
PreGenie: An Agentic Framework for High-quality Visual Presentation Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Visual presentations are vital for effective communication, but they are limited by their complexity and lack of visual understanding.
Approach: a new framework is proposed to generate high-quality visual presentations using multimodal large language models.
Outcome: The proposed framework outperforms existing models in multimodal understanding and content consistency.
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size.
Approach: They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding.
Outcome: The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models.

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