activity
20242026
collaborators

7 papers

cs.AI2026

FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks

Yupeng Cao, Haohang Li, Weijin Liu +11

Recent studies demonstrate that tool-calling capability enables large language models (LLMs) to interact with external environments for long-horizon financial tasks. While existing…

cs.CL2026

MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment

Yupeng Cao, Chengyang He, Yangyang Yu +2

Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in automated veracity assessment,…

cs.CL2026

Listen to the Layers: Mitigating Hallucinations with Inter-Layer Disagreement

Koduvayur Subbalakshmi, Sabbir Hossain Ujjal, Venkata Krishna Teja Mangichetty +1

Pretrained Large Language Models (LLMs) are prone to generating fluent yet factually incorrect text-a phenomenon known as hallucinations, undermining their reliability and utility…

cs.CE2025

FinAudio: A Benchmark for Audio Large Language Models in Financial Applications

Yupeng Cao, Haohang Li, Yangyang Yu +10

Audio Large Language Models (AudioLLMs) have received widespread attention and have significantly improved performance on audio tasks such as conversation, audio understanding, and…

cs.LG2025

SALMAN: Stability Analysis of Language Models Through the Maps Between Graph-based Manifolds

Wuxinlin Cheng, Yupeng Cao, Jinwen Wu +3

Recent strides in pretrained transformer-based language models have propelled state-of-the-art performance in numerous NLP tasks. Yet, as these models grow in size and deployment,…

q-fin.RM2025

RiskLabs: Predicting Financial Risk Using Large Language Model based on Multimodal and Multi-Sources Data

Yupeng Cao, Zhi Chen, Prashant Kumar +7

The integration of Artificial Intelligence (AI) techniques, particularly large language models (LLMs), in finance has garnered increasing academic attention. Despite progress, exis…