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

• URL: http://arxiv.org/abs/2512.20082v2
• Date: Wed, 24 Dec 2025 03:42:59 GMT
• Title: Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches
• Authors: Chaithra, Kamesh Kadimisetty, Biju R Mohan,
• Abstract summary: Existing works in financial sentiment analysis have not considered the impact of stock prices or market feedback on sentiment analysis.<n>We propose an adaptive framework that integrates large language models (LLMs) with real-world stock market feedback to improve sentiment classification.
• Score: 1.9116784879310027
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• $φ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models [58.217707070069885]
  This paper presents a novel Fairness Direct Preference Optimization (FaiDPO or $$-DPO) framework for continual learning in LMMs.<n>We first propose a new continual learning paradigm based on Direct Preference Optimization (DPO) to mitigate catastrophic forgetting by aligning learning with pairwise preference signals.<n> Extensive experiments and ablation studies show the proposed $$-DPO achieves State-of-the-Art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-02-26T04:14:33Z)
• Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading [57.28635022507172]
  TiMi is a rationality-driven multi-agent system that architecturally decouples strategy development from minute-level deployment.<n>We propose a two-tier analytical paradigm from macro patterns to micro customization, layered programming design for trading bot implementation, and closed-loop optimization driven by mathematical reflection.
  arXiv  Detail & Related papers  (2025-10-06T13:08:55Z)
• Reinforcement Learning-Based Market Making as a Stochastic Control on Non-Stationary Limit Order Book Dynamics [0.0]
  Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies.<n>This paper explores the integration of a reinforcement learning agent in a market-making context.
  arXiv  Detail & Related papers  (2025-09-15T21:08:13Z)
• Your AI, Not Your View: The Bias of LLMs in Investment Analysis [62.388554963415906]
  In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data.<n>These conflicts are especially problematic in real-world investment services, where a model's inherent biases can misalign with institutional objectives.<n>We propose an experimental framework to investigate emergent behaviors in such conflict scenarios, offering a quantitative analysis of bias in investment analysis.
  arXiv  Detail & Related papers  (2025-07-28T16:09:38Z)
• FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMs [2.06242362470764]
  We introduce FinDPO, the first finance-specific sentiment analysis framework based on post-training human preference alignment.<n>The proposed FinDPO achieves state-of-the-art performance on standard sentiment classification benchmarks.<n>We show that FinDPO is the first sentiment-based approach to maintain substantial positive returns of 67% annually and strong risk-adjusted performance.
  arXiv  Detail & Related papers  (2025-07-24T13:57:05Z)
• Deriving Strategic Market Insights with Large Language Models: A Benchmark for Forward Counterfactual Generation [55.2788567621326]
  We introduce a novel benchmark, FIN-FORCE-FINancial FORward Counterfactual Evaluation.<n>By curating financial news headlines, FIN-FORCE supports LLM based forward counterfactual generation.<n>This paves the way for scalable and automated solutions for exploring and anticipating future market developments.
  arXiv  Detail & Related papers  (2025-05-26T02:41:50Z)
• Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach [6.112119533910774]
  This paper introduces an advanced approach by employing Large Language Models (LLMs) instruction fine-tuned with a novel combination of instruction-based techniques and quantized low-rank adaptation (QLoRA) compression. Our methodology integrates 'base factors', such as financial metric growth and earnings transcripts, with 'external factors', including recent market indices performances and analyst grades, to create a rich, supervised dataset. This study not only demonstrates the power of integrating cutting-edge AI with fine-tuned financial data but also paves the way for future research in enhancing AI-driven financial analysis tools.
  arXiv  Detail & Related papers  (2024-08-13T04:53:31Z)
• AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework [48.3060010653088]
  We release AlphaFin datasets, combining traditional research datasets, real-time financial data, and handwritten chain-of-thought (CoT) data. We then use AlphaFin datasets to benchmark a state-of-the-art method, called Stock-Chain, for effectively tackling the financial analysis task.
  arXiv  Detail & Related papers  (2024-03-19T09:45:33Z)
• Transforming Sentiment Analysis in the Financial Domain with ChatGPT [0.07499722271664146]
  This study investigates the potential of large language models, particularly ChatGPT 3.5, in financial sentiment analysis. ChatGPT exhibited approximately 35% enhanced performance in sentiment classification and a 36% higher correlation with market returns. By underlining the significance of prompt engineering, particularly in zero-shot contexts, this study spotlights ChatGPT's potential to substantially boost sentiment analysis in financial applications.
  arXiv  Detail & Related papers  (2023-08-13T09:20:47Z)
• HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE [113.47287249524008]
  It is still an open question to build a factor model that can conduct stock prediction in an online and adaptive setting. We propose the first deep learning based online and adaptive factor model, HireVAE, at the core of which is a hierarchical latent space that embeds the relationship between the market situation and stock-wise latent factors. Across four commonly used real stock market benchmarks, the proposed HireVAE demonstrate superior performance in terms of active returns over previous methods.
  arXiv  Detail & Related papers  (2023-06-05T12:58:13Z)
• Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models [48.87381259980254]
  We document the capability of large language models (LLMs) like ChatGPT to predict stock market reactions from news headlines without direct financial training.<n>Using post-knowledge-cutoff headlines, GPT-4 captures initial market responses, achieving approximately 90% portfolio-day hit rates for the non-tradable initial reaction.
  arXiv  Detail & Related papers  (2023-04-15T19:22:37Z)
• Deep learning based Chinese text sentiment mining and stock market correlation research [6.000327333763521]
  We explore how to crawl financial forum data such as stock bars and combine them with deep learning models for sentiment analysis. In this paper, we will use the BERT model to train against the financial corpus and predict the SZSE Component Index. The obtained sentiment features will be able to reflect the fluctuations in the stock market and help to improve the prediction accuracy effectively.
  arXiv  Detail & Related papers  (2022-05-10T08:35:33Z)
• A Sentiment Analysis Approach to the Prediction of Market Volatility [62.997667081978825]
  We have explored the relationship between sentiment extracted from financial news and tweets and FTSE100 movements. The sentiment captured from news headlines could be used as a signal to predict market returns; the same does not apply for volatility. We developed an accurate classifier for the prediction of market volatility in response to the arrival of new information.
  arXiv  Detail & Related papers  (2020-12-10T01:15:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.