Publications

FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design

Y. Jiang, et al.

Poster presentation at AAAI Spring Symposium on Human-Like Learning 2024

Poster presentation at LLM Agents Workshop @ ICLR 2024

Accepted by IEEE Transactions on Big Data

AAAI Poster ICLR Workshop Publication Source Code

FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making

Y. Jiang, et al.

Poster presentation at NeurIPS 2024

Publication

Moira: Belief Revision and Policy Memory through Counterfactual Reflection for Pair Trading

P. Giannouris, Y. Jiang, et al.

Publication

Enhancing Financial Time-Series Forecasting with Retrieval-Augmented Large Language Models

M. Xiao, …, Y. Jiang, et al.

Publication Source Code

RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection

Z. Liu, …, Y. Jiang, et al.

Publication

MFMDQwen: Multilingual Financial Misinformation Detection Based on Large Language Model

Z. Liu, Y. Wang, Y. Jiang, et al.

Publication

AutoRedTrader: Autonomous Red Teaming of Trading Agents through Synthetic Misinformation Injection

Z. Liu, …, Y. Jiang, et al.

Publication

FinBen: A Holistic Financial Benchmark for Large Language Models

Q. Xie, …, Y. Jiang, et al.

Poster presentation at NeurIPS 2024 Datasets and Benchmarks

Leaderboard Publication Source Code

InvestorBench: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent

H. Li, …, Y. Jiang, et al.

Accepted by Association for Computational Linguistics 2025

Publication Source Code

All That Glisters Is Not Gold: A Benchmark for Reference-Free Counterfactual Financial Misinformation Detection

Y. Jiang, et al.

Oral presentation at Association for Computational Linguistics (ACL) 2026

Publication Source Code

MultiFinBen: A Multilingual, Multimodal, and Difficulty-Aware Benchmark for Financial LLM Evaluation

X. Peng, …, Y. Jiang, et al.

Oral presentation at Association for Computational Linguistics (ACL) 2026

Publication Source Code

Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection

Z. Liu, Y. Cao, Y. Jiang, et al.

Accepted by ACL 2026 Findings

Publication

Appear2Meaning: A Cross-Cultural Benchmark for Structured Cultural Metadata Inference from Images

Y. Jiang, et al.

Publication Source Code

Herculean: An Agentic Benchmark for Financial Intelligence

X. Peng, …, Y. Jiang, et al.

Publication