Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches

TL;DR

This paper introduces an adaptive financial sentiment analysis framework that combines instruction-tuned large language models, retrieval-augmented generation, and reinforcement learning to improve sentiment classification accuracy and market relevance in the Indian stock market.

Contribution

It presents a novel integration of LLM fine-tuning, dynamic retrieval, and reinforcement learning for market-aware sentiment analysis, addressing limitations of previous static models.

Findings

Significant improvement in sentiment classification accuracy.

Enhanced alignment between sentiment predictions and stock market movements.

Effective adaptation to market dynamics through reinforcement learning.

Abstract

Financial sentiment analysis plays a crucial role in informing investment decisions, assessing market risk, and predicting stock price trends. Existing works in financial sentiment analysis have not considered the impact of stock prices or market feedback on sentiment analysis. In this paper, we propose an adaptive framework that integrates large language models (LLMs) with real-world stock market feedback to improve sentiment classification in the context of the Indian stock market. The proposed methodology fine-tunes the LLaMA 3.2 3B model using instruction-based learning on the SentiFin dataset. To enhance sentiment predictions, a retrieval-augmented generation (RAG) pipeline is employed that dynamically selects multi-source contextual information based on the cosine similarity of the sentence embeddings. Furthermore, a feedback-driven module is introduced that adjusts the reliability of the source by comparing predicted sentiment with actual next-day stock returns, allowing the system to iteratively adapt to market behavior. To generalize this adaptive mechanism across temporal data, a reinforcement learning agent trained using proximal policy optimization (PPO) is incorporated. The PPO agent learns to optimize source weighting policies based on cumulative reward signals from sentiment-return alignment. Experimental results on NIFTY 50 news headlines collected from 2024 to 2025 demonstrate that the proposed system significantly improves classification accuracy, F1-score, and market alignment over baseline models and static retrieval methods. The results validate the potential of combining instruction-tuned LLMs with dynamic feedback and reinforcement learning for robust, market-aware financial sentiment modeling.