# L3iTC at the FinLLM Challenge Task: Quantization for Financial Text Classification & Summarization

arXiv: https://arxiv.org/abs/2408.03033 · HTML: https://mlsanity.com/paper/2408.03033/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 6 Aug 2024.

## Builds on (most cited first, 5 of 5)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design](https://mlsanity.com/paper/2311.13743/) (2023)
- [Skywork: A More Open Bilingual Foundation Model](https://mlsanity.com/paper/2310.19341/) (2023)
- [Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading](https://mlsanity.com/paper/2105.12825/) (2021)

## Built on by (most cited first, 4 of 4)

- [LLM Bias Detection and Mitigation through the Lens of Desired Distributions](https://mlsanity.com/paper/2510.06354/) (2025)
- [HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization](https://mlsanity.com/paper/2507.18560/) (2025)
- [A symbolic Perl algorithm for the unification of Nahuatl word spellings](https://mlsanity.com/paper/2511.19118/) (2025)
- [RA-FinBERT: Rule-aware LoRA adaptation for low-resource financial sentiment classification](https://mlsanity.com/paper/2608.09834/) (2026)

## Abstract (arXiv)

This article details our participation (L3iTC) in the FinLLM Challenge Task 2024, focusing on two key areas: Task 1, financial text classification, and Task 2, financial text summarization. To address these challenges, we fine-tuned several large language models (LLMs) to optimize performance for each task. Specifically, we used 4-bit quantization and LoRA to determine which layers of the LLMs should be trained at a lower precision. This approach not only accelerated the fine-tuning process on the training data provided by the organizers but also enabled us to run the models on low GPU memory. Our fine-tuned models achieved third place for the financial classification task with an F1-score of 0.7543 and secured sixth place in the financial summarization task on the official test datasets.