# Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately

arXiv: https://arxiv.org/abs/2402.01722 · HTML: https://mlsanity.com/paper/2402.01722/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 10 references that are in the map.
- First posted on arXiv 27 Jan 2024.

## Builds on (most cited first, 2 of 2)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)

## Built on by (most cited first, 21 of 21)

- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems](https://mlsanity.com/paper/2502.00409/) (2025)
- [Mixture of In-Context Experts Enhance LLMs' Long Context Awareness](https://mlsanity.com/paper/2406.19598/) (2024)
- [SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment](https://mlsanity.com/paper/2509.03934/) (2025)
- [Retrieval-Augmented Test Generation: How Far Are We?](https://mlsanity.com/paper/2409.12682/) (2024)
- [Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels](https://mlsanity.com/paper/2509.16596/) (2025)
- [Fine-Tuning or Fine-Failing? Debunking Performance Myths in Large Language Models](https://mlsanity.com/paper/2406.11201/) (2024)
- [GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2407.04528/) (2024)
- [GUNDAM: Aligning Large Language Models with Graph Understanding](https://mlsanity.com/paper/2409.20053/) (2024)
- [WeQA: A Benchmark for Retrieval Augmented Generation in Wind Energy Domain](https://mlsanity.com/paper/2408.11800/) (2024)
- [Fine-Tuning LLMs for Reliable Medical Question-Answering Services](https://mlsanity.com/paper/2410.16088/) (2024)
- [Efficient Compositional Multi-tasking for On-device Large Language Models](https://mlsanity.com/paper/2507.16083/) (2025)
- [ChemQuests: A Curated Chemistry Question-Answer Database Extracted from ChemRxiv papers](https://mlsanity.com/paper/2505.05232/) (2025)
- [KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance](https://mlsanity.com/paper/2505.15480/) (2025)
- [60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering](https://mlsanity.com/paper/2409.15825/) (2024)
- [Typed-RAG: Type-Aware Decomposition of Non-Factoid Questions for Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.15879/) (2025)
- [Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learning](https://mlsanity.com/paper/2505.11758/) (2025)
- [A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA)](https://mlsanity.com/paper/2512.03887/) (2025)
- [From Divergence to Consensus: Evaluating the Role of Large Language Models in Facilitating Agreement through Adaptive Strategies](https://mlsanity.com/paper/2503.15521/) (2025)
- [Exploring NLP Benchmarks in an Extremely Low-Resource Setting](https://mlsanity.com/paper/2509.03962/) (2025)
- [Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices](https://mlsanity.com/paper/2606.20571/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models. The objective is to enhance AI models through continuous feedback loops, utilizing metrics such as cosine similarity, LLM evaluation and Rouge-L scores to evaluate the models. Leveraging LLMs like GPT-3.5, GPT4ALL, and LLaMA2, and Claude, this approach is benchmarked on financial datasets, including the FinanceBench and RAG Instruct Benchmark Tester Dataset, illustrating the necessity of fine-tuning. The results showcase the capability of fine-tuned models to surpass the accuracy of zero-shot LLMs, providing superior question and answering capabilities. Notably, the combination of fine-tuning the LLM with a process known as Retrieval Augmented Generation (RAG) proves to generate responses with improved accuracy.