paper-with-me

Papers

Learning to Trade Like an Expert: Cognitive Fine-Tuning for Stable Financial Reasoning in Language Models

2026-04-18 · Yuchen Pan, Soung Chang Liew arxiv

Recent deployments of large language models (LLMs) as autonomous trading agents raise questions about whether financial decision-making competence generalizes beyond specific market patterns and how it should be trained and evaluated in noisy markets lacking ground truth. We propose a structured framework for training and evaluating such models. Central to our approach is a curated, multiple-choice question (MCQ) dataset derived from classic textbooks and historical markets, verified by an AI committee, enriched with structured reasoning traces, and augmented to reduce shortcut learning. To evaluate whether performance on isolated MCQs generalizes to real-world trading, we introduce a two-stage protocol combining test-set evaluation with an MCQ-based chronological trading simulation. Extensive evaluations across market regimes provide statistically robust evidence that open models trained with our framework exhibit competitive, risk-aware behavior over time, outperform open-source baselines, and approach frontier-model performance at smaller scale. We release the dataset and evaluation framework to support further research.

📄 PDF Abstract BibTeX arXiv:2604.16862

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts

2025-11-24 · Yasin Esfandiari, Stefan Bauer, Sebastian U. Stich, Andrea Dittadi arxiv

Diffusion models for image generation often exhibit a trade-off between perceptual sample quality and data likelihood: training objectives emphasizing high-noise denoising steps yield realistic images but poor likelihood…

Image Generation

DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding

2025-03-17 · Xinyu Ma, Ziyang Ding, Zhicong Luo, Chi Chen 외

Human experts excel at fine-grained visual discrimination by leveraging domain knowledge to refine perceptual features, a capability that remains underdeveloped in current Multimodal Large Language Models (MLLMs). Despit…

Domain GeneralizationMultimodal ReasoningVisual Grounding

Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs

2024-07-12 · Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li 외

Recent advancements in LLMs have showcased their remarkable role-playing capabilities, able to accurately simulate the dialogue styles and cognitive processes of various roles based on different instructions and contexts…

Exploiting the Experts: Unauthorized Compression in MoE-LLMs

2025-11-22 · Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha, Rajiv Ramnath arxiv

Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a unique vulnerability: adversaries can at…

Active Learning

Think Twice to See More: Iterative Visual Reasoning in Medical VLMs

2025-10-11 · Kaitao Chen, Shaohao Rui, Yankai Jiang, Jiamin Wu 외 arxiv

Medical vision-language models (VLMs) excel at image-text understanding but typically rely on a single-pass reasoning that neglects localized visual cues. In clinical practice, however, human experts iteratively scan, fo…

Visual Question AnsweringReinforcement LearningVisual GroundingVisual Reasoning