Papers by Feiyu Zhao

8 papers
HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on hallucination focus on text or vision, while few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth.
Approach: They propose a large-scale benchmark for evaluating hallucinations across speech, sound, and music.
Outcome: The proposed model improves hallucination rate, yes/no bias, error-type analysis, and refusal rate.
Graph Convolution for Multimodal Information Extraction from Visually Rich Documents (N19-2)

Copied to clipboard

Challenge: Visually rich documents (VRDs) present information in the form of both text and vision.
Approach: They propose a graph convolution based model to combine textual and visual information presented in VRDs.
Outcome: The proposed model outperforms existing models on two real-world datasets.
DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback (2025.findings-emnlp)

Copied to clipboard

Challenge: Multi-agent systems (MAS) powered by large language models struggle to adapt to evolving task dependencies and to handle uncertainties.
Approach: They propose a Dynamic Environment-Aware Manager-Player Agents Coordination framework that enhances multi-agent coordination through long-term strategic planning.
Outcome: The proposed framework outperforms traditional reinforcement learning and human-agent collaboration in the Overcooked simulation.
Attribution and Application of Multiple Neurons in Multimodal Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to identify multimodal neurons in MLLMs are insufficiently understood . previous studies focused on identifying neurons corresponding to single-tokens .
Approach: They propose a method to identify multimodal neurons in Transformer-based MLLMs . they introduce fuzzy set theory to model the complex relationship between neurons and semantic concepts .
Outcome: The proposed method improves performance on the Visual Question Answering task.
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for text chunking are limited by text chunks and lack of domain-specific knowledge.
Approach: They propose a dual-metric evaluation method to quantify text chunking quality . they aim to generate a structured list of chunking regular expressions .
Outcome: The proposed method enables direct quantification of chunking quality . it substantiates the need to integrate LLMs into chunking process .
H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)

Copied to clipboard

Challenge: Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime .
Approach: They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM .
Outcome: Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets .
Inside Out: Evolving User-Centric Core Memory Trees for Long-Term Personalized Dialogue Systems (2026.acl-long)

Copied to clipboard

Challenge: Existing personalized dialogue systems struggle to reconcile unbounded interactions with finite context constraints.
Approach: They propose a framework that utilizes a globally maintained PersonaTree as the carrier of long-term user profiling.
Outcome: The proposed framework outperforms existing systems in suppressing contextual noise and persona inconsistency.
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs .
Approach: They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service .
Outcome: The proposed benchmark evaluates the security of RAG against 14 representative RAG components.

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