Papers by Yongqi Zhang

32 papers
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)

Copied to clipboard

Challenge: Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency.
Approach: They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters.
Outcome: The proposed model breaks the impossible triangle of latency, accuracy, and complexity.
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach: They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome: The proposed model performs better on 200K hours of 6-language data for voice generation applications.
Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing graph neural networks (GNNs) adopt rigid, query-agnostic path-exploration strategies limiting their ability to adapt to diverse linguistic contexts and semantic nuances.
Approach: They propose a mixture-of-experts framework that personalizes path exploration . framework uses length experts that adaptively selects and weights candidate paths . it also uses pruning experts that evaluates candidate path from a complementary perspective .
Outcome: The proposed framework shows superior performance on a diverse benchmark . it uses a mixture of experts that weights and selects path lengths according to query complexity .
MedOdyssey: A Medical Domain Benchmark for Long Context Evaluation Up to 200K Tokens (2025.findings-naacl)

Copied to clipboard

Challenge: Existing benchmarks in the generic domain have evaluated long-context capabilities for LLMs.
Approach: They propose a medical long-context benchmark with seven length levels ranging from 4K to 200K tokens.
Outcome: The proposed benchmarks have seven length levels ranging from 4K to 200K tokens.
Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models are reshaping internet services, and serving them is costly.
Approach: They propose an efficient distributed LLM serving system that splits prefill and decode requests into smaller chunks .
Outcome: The proposed system reduces TTFT, TPOT, and latency compared to the state-of-the-art system.
FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph (2026.acl-long)

Copied to clipboard

Challenge: Equity research reports are crucial resources for investors, but lack professional analysis and the rapid evolution of market events outpaces their update cycles.
Approach: They propose an event-Enhanced automated construction of financial knowledge graph (FinKario) that automatically integrates real-time company fundamentals and market events through prompt-driven extraction guided by professional institutional templates.
Outcome: The proposed model outperforms financial LLMs by 18.81% and institutional strategies by 17.85% on average in backtesting.
Balancing Knowledge Breadth and Task Depth for Effective Domain Adaptation Fine-Tuning (2026.findings-acl)

Copied to clipboard

Challenge: a lack of knowledge breadth and task depth can hinder curriculum learning in domains such as medicine and finance.
Approach: They propose a two-dimensional curriculum learning framework that coordinates model training along two orthogonal axes: the knowledge dimension and the task dimension.
Outcome: The proposed framework improves accuracy on medical evaluations by 2.49% and on financial evaluations 1.2% compared with the second-best method.
ArchiDocGen: Multi-Agent Framework for Expository Document Generation in the Architectural Industry (2025.acl-industry)

Copied to clipboard

Challenge: drafting method statements is labor-intensive and time-consuming . traditional methods involve using static templates filled in manually by engineers .
Approach: They propose a framework that automates method statement generation by using multi-agent collaboration.
Outcome: The proposed framework achieves 4.38 ContentScore, excelling in specialization, completeness, organization, and clarity.
Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in machine translation have focused on a single pre-trained decoder . encoder-decoder architectures have received relatively little attention in NMT .
Approach: They propose a method that leverages LLMs as MT encoders and pairs them with lightweight decoders to develop universal translation models.
Outcome: The proposed method matches or surpasses baselines in terms of translation quality but achieves 75% reduction in memory footprint of the KV cache.
Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)

Copied to clipboard

Challenge: Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios .
Approach: They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets .
Outcome: The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files.
Learning to Describe for Predicting Zero-shot Drug-Drug Interactions (2023.emnlp-main)

Copied to clipboard

Challenge: Existing computational methods for DDI prediction fail to capture interactions for new drugs due to the lack of knowledge.
Approach: They propose a problem setup as zero-shot DDI prediction that deals with the case of new drugs by using textual information from online databases.
Outcome: The proposed method improves on several settings including zero-shot and few-shot DDI prediction and the selected texts are semantically relevant.
R2AG: Incorporating Retrieval Information into Retrieval Augmented Generation (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to augment large language models with external documents are lacking in the semantic gap between LLMs and retrievers due to differences in their training objectives and architectures.
Approach: They propose to integrate R2AG into R2etrieval augmented generation framework by using a R2-Former to capture retrieval information.
Outcome: The proposed framework fills the semantic gap between LLMs and retrievers due to differences in their training objectives and architectures.
Understanding Conflicts in Multi-Objective Alignment through Reward Consistency (2026.findings-acl)

Copied to clipboard

Challenge: Existing training pipelines still face alignment conflicts where optimizing for one objective degrades performance on others.
Approach: They propose a reward-based criterion that approximates alignment conflicts via reward models.
Outcome: The proposed framework improves harmlessness and helpfulness scores by 23.07% over the vanilla dataset.
CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation (2025.findings-acl)

Copied to clipboard

Challenge: Medical quality control indicators are essential to assess the qualifications of healthcare institutions for medical services.
Approach: They propose a Chinese electronic medical records-based dataset for MQCIC and propose CF-IR method that disentangles clinical fact verification and inferential rule reasoning actions.
Outcome: The proposed method outperforms Chain-of-Thought methods on 20 representative LLMs, covering general and medical models.
A Survey on Training-free Alignment of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms.
Approach: They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration .
Outcome: The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining .
EfficientTool: A Cost-Effective Aligning Framework for Tool-Conditioned Agents in SME Scenarios (2026.acl-industry)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly adopted in downstream industries, yet aligning proprietary agents remains challenging.
Approach: They propose a cost-effective, tool-conditioned alignment framework that forms a closed loop over data collection, iterative training, and deployment-oriented evaluation.
Outcome: The proposed framework effectively aligns model in SME scenarios while preserving general tool-calling capability.
BubbleRAG: Interactive Cognitive Offloading with Thought Bubble in Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Retrieval-augmented generation (RAG) extends the capabilities of large language models (LLMs) by providing access to external knowledge.
Approach: They propose a framework that emulates human interactive reading through annotation and re-reading by integrating a thought bubble module that offloads internal cognition into external bookmark tokens, which are then annotated back into the context.
Outcome: The proposed framework offloads internal cognition into external bookmark tokens, which are then annotated back into the context.
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) often refuse to answer legitimate queries, causing models to treat many reasonable prompts as potentially risky.
Approach: They propose a framework that automatically generates and selects overrefusal prompts near the safety boundary.
Outcome: The proposed framework identifies and curates boundary-aligned prompts, enabling more effective and targeted mitigation of overrefusal.
BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment (2025.naacl-long)

Copied to clipboard

Challenge: Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years.
Approach: They propose a method to balance the number of prompts and responses to improve knowledge breadth and knowledge depth by introducing gradient-based clustering to estimate the knowledge informativeness and usefulness of each augmented sample.
Outcome: The proposed method outperforms baseline methods while maintaining training efficiency.
BP4ER: Bootstrap Prompting for Explicit Reasoning in Medical Dialogue Generation (2024.lrec-main)

Copied to clipboard

Challenge: Medical dialogue generation (MDG) has gained increasing attention due to its substantial practical value.
Approach: They propose a method which explicitly models MDG’s multi-step reasoning process and iteratively enhances this reasoning process.
Outcome: The proposed method outperforms state-of-the-art methods across objective and subjective evaluations on two publicly available datasets.
DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision (2025.emnlp-industry)

Copied to clipboard

Challenge: Recent advances in outcome-supervised reinforcement learning (RL) have shown strong performance, but this approach still suffers from inefficient exploration, sparse reward signals, and ambiguous global reward feedback.
Approach: They propose a model that models RAG as a Markov Decision Process (MDP) and introduces an efficient pruning strategy to optimize data expansion.
Outcome: The proposed model outperforms existing methods and achieves an average performance improvement of 6.2% across six datasets.
An LLM-based Framework for Biomedical Terminology Normalization in Social Media via Multi-Agent Collaboration (2025.coling-main)

Copied to clipboard

Challenge: Experimental results indicate that our approach exhibits competitive performance.
Approach: They propose a tuning-free approach to normalize non-standard terms using large language models . they use a search engine and a domain knowledge base to expand the short texts into accurate descriptions .
Outcome: The proposed approach is based on the "Recall and Re-rank" framework . it can be used to identify the standard term in a specified termbase for non-standardized mentions .
LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review (2025.acl-demo)

Copied to clipboard

Challenge: Large language models (LLMs) are capable of generating inaccurate discharge summary content or fabricating information without valid sources.
Approach: They propose a tool for empowering LLMs with Logic-Controlled Discharge Summary generation.
Outcome: The proposed tool identifies the writing logic of discharge summaries and integrates it with EMRs to generate silver discharge summararies.
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research (2025.findings-emnlp)

Copied to clipboard

Challenge: a rapid advancement of perovskite solar cells has led to an exponential growth in research publications.
Approach: They propose a knowledge-enhanced system for perovskite solar cells that integrates three key components.
Outcome: The proposed system outperforms existing models in domain-specific knowledge retrieval and scientific reasoning tasks.
Relation-aware Ensemble Learning for Knowledge Graph Embedding (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to explore semantics of knowledge graphs have been proposed to explore these semantics in distinct ways.
Approach: They propose to leverage existing methods in relation-aware manner to learn an ensemble by leveraging existing methods.
Outcome: The proposed method has the same computation cost as general ensemble methods but with much better performance on benchmark datasets.
MCLE-Mol: Empowering LLM with Molecular Comprehension and Low-Cost Continual Evolution for Interpretable Property Prediction (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) offer a new paradigm for molecular property prediction (MPP), yet a semantic gap between natural language and molecul representations limits their ability to capture structure–activity relationships (SAR).
Approach: They propose an ML–LLM–Rule collaborative framework for MPP that injects ML-derived substructure attribution values into LLMs and calibrates them under specific chemical contexts.
Outcome: The proposed framework outperforms baseline models on multiple benchmark datasets and is highly interpretable.
SecureSQL: Evaluating Data Leakage of Large Language Models as Natural Language Interfaces to Databases (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing studies on the vulnerability of large language models to SQL injection have been limited.
Approach: They propose to evaluate the potential of language models to leak sensitive data when generating SQL queries.
Outcome: The proposed model with the best performance has an accuracy of 61.7%, compared to humans who achieve 94% accuracy.
Efficient Hyper-parameter Search for Knowledge Graph Embedding (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for learning knowledge graphs do not search hyper-parameters efficiently.
Approach: They propose an efficient two-stage search algorithm which explores HP configurations on small subgraph and transfers top-performed configurations for fine-tuning on large full graph.
Outcome: The proposed method finds better HPs than baseline algorithms within the same time budget and achieves 9.1% relative improvement on large-scale knowledge graphs.
Robust Singing Voice Transcription Serves Synthesis (2024.acl-long)

Copied to clipboard

Challenge: Current AST methods struggle with accuracy and robustness when used for practical annotation.
Approach: They propose a model that converts singing recordings into note sequences for automatic annotation of singing datasets.
Outcome: The proposed model outperforms baseline models on enlarged, automatically annotated datasets.
Distillation Enhanced Generative Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target.
Approach: They propose a framework that leverages generative language models to enhance generative retrieval by distillation.
Outcome: The proposed framework achieves state-of-the-art performance among the generative retrieval methods.
Text-to-Song: Towards Controllable Music Generation Incorporating Vocal and Accompaniment (2024.acl-long)

Copied to clipboard

Challenge: Existing studies focus on singing voice synthesis and music generation independently.
Approach: They propose a novel task called Text-to-Song synthesis which incorporates both vocal and accompaniment generation.
Outcome: The proposed method can synthesize songs with comparable quality and style consistency.
Towards Text-Image Interleaved Retrieval (2025.acl-long)

Copied to clipboard

Challenge: Existing multimodal information retrieval models rely on single-image inputs . current models use a dense retrieval paradigm, but this approach is not effective .
Approach: They propose a text-image interleaved retrieval task where query and document are interleaves . they adapt off-the-shelf retrievers and build a dense baseline by interleaded multimodal large language model .
Outcome: The proposed model achieves significant improvements over the baseline by substantially fewer visual tokens.

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