# FineTuneBench: How well do commercial fine-tuning APIs infuse knowledge into LLMs?

arXiv: https://arxiv.org/abs/2411.05059 · HTML: https://mlsanity.com/paper/2411.05059/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs](https://mlsanity.com/paper/2312.05934/) (2023)
- [Removing RLHF Protections in GPT-4 via Fine-Tuning](https://mlsanity.com/paper/2311.05553/) (2023)
- [Orca 2: Teaching Small Language Models How to Reason](https://mlsanity.com/paper/2311.11045/) (2023)
- [ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence](https://mlsanity.com/paper/2404.10198/) (2024)
- [INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models](https://mlsanity.com/paper/2306.04757/) (2023)
- [Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers](https://mlsanity.com/paper/2005.11787/) (2020)
- [Fine-tuning ChatGPT for Automatic Scoring](https://mlsanity.com/paper/2310.10072/) (2023)
- [How well do LLMs cite relevant medical references? An evaluation framework and analyses](https://mlsanity.com/paper/2402.02008/) (2024)
- [Fine-tuning GPT-3 for Russian Text Summarization](https://mlsanity.com/paper/2108.03502/) (2021)
- [Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?](https://mlsanity.com/paper/2307.16382/) (2023)
- [Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection](https://mlsanity.com/paper/2410.02330/) (2024)

## Built on by (most cited first, 12 of 12)

- [Lessons from Studying Two-Hop Latent Reasoning](https://mlsanity.com/paper/2411.16353/) (2024)
- [Data Mixing Optimization for Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2508.11953/) (2025)
- [Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs](https://mlsanity.com/paper/2502.14828/) (2025)
- [Can Large Language Models Match the Conclusions of Systematic Reviews?](https://mlsanity.com/paper/2505.22787/) (2025)
- [Supervised Fine-Tuning LLMs to Behave as Pedagogical Agents in Programming Education](https://mlsanity.com/paper/2502.20527/) (2025)
- [Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime](https://mlsanity.com/paper/2508.06178/) (2025)
- [From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization](https://mlsanity.com/paper/2510.19036/) (2025)
- [ECG-LLM -- training and evaluation of domain-specific large language models for electrocardiography](https://mlsanity.com/paper/2510.18339/) (2025)
- [Latent Knowledge as a Predictor of Fact Acquisition in Fine-Tuned Large Language Models](https://mlsanity.com/paper/2601.18468/) (2026)
- [Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning](https://mlsanity.com/paper/2604.06385/) (2026)
- [Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications](https://mlsanity.com/paper/2605.09533/) (2026)
- [Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning](https://mlsanity.com/paper/2609.09553/) (2026)

## Abstract (arXiv)

There is great interest in fine-tuning frontier large language models (LLMs) to inject new information and update existing knowledge. While commercial LLM fine-tuning APIs from providers such as OpenAI and Google promise flexible adaptation for various applications, the efficacy of fine-tuning remains unclear. In this study, we introduce FineTuneBench, an evaluation framework and dataset for understanding how well commercial fine-tuning APIs can successfully learn new and updated knowledge. We analyze five frontier LLMs with commercially available fine-tuning APIs, including GPT-4o and Gemini 1.5 Pro, on their effectiveness in two settings: (1) ingesting novel information, such as recent news events and new people profiles, and (2) updating existing knowledge, such as updated medical guidelines and code frameworks. Our results reveal substantial shortcomings in all the models' abilities to effectively learn new information through fine-tuning, with an average generalization accuracy of 37% across all models. When updating existing knowledge, such as incorporating medical guideline updates, commercial fine-tuning APIs show even more limited capability (average generalization accuracy of 19%). Overall, fine-tuning GPT-4o mini is the most effective for infusing new knowledge and updating knowledge, followed by GPT-3.5 Turbo and GPT-4o. The fine-tuning APIs for Gemini 1.5 Flesh and Gemini 1.5 Pro are unable to learn new knowledge or update existing knowledge. These findings underscore a major shortcoming in using current commercial fine-tuning services to achieve reliable knowledge infusion in common scenarios. We open source the FineTuneBench dataset at https://github.com/kevinwu23/StanfordFineTuneBench.