# Do Influence Functions Work on Large Language Models?

arXiv: https://arxiv.org/abs/2409.19998 · HTML: https://mlsanity.com/paper/2409.19998/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [Studying Large Language Model Generalization with Influence Functions](https://mlsanity.com/paper/2308.03296/) (2023)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Scaling Laws for Transfer](https://mlsanity.com/paper/2102.01293/) (2021)
- [LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B](https://mlsanity.com/paper/2310.20624/) (2023)
- [Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2110.14049/) (2021)
- [If Influence Functions are the Answer, Then What is the Question?](https://mlsanity.com/paper/2209.05364/) (2022)
- [Scaling Up Influence Functions](https://mlsanity.com/paper/2112.03052/) (2021)

## Built on by (most cited first, 20 of 20)

- [Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models](https://mlsanity.com/paper/2605.11887/) (2026)
- [Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler](https://mlsanity.com/paper/2510.27172/) (2025)
- [Better Training Data Attribution via Better Inverse Hessian-Vector Products](https://mlsanity.com/paper/2507.14740/) (2025)
- [Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution](https://mlsanity.com/paper/2602.14869/) (2026)
- [IF-GUIDE: Influence Function-Guided Detoxification of LLMs](https://mlsanity.com/paper/2506.01790/) (2025)
- [Fast Data Attribution for Text-to-Image Models](https://mlsanity.com/paper/2511.10721/) (2025)
- [First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation](https://mlsanity.com/paper/2511.04715/) (2025)
- [Scalable Valuation of Human Feedback through Provably Robust Model Alignment](https://mlsanity.com/paper/2505.17859/) (2025)
- [Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing](https://mlsanity.com/paper/2510.02334/) (2025)
- [Z0-Inf: Zeroth Order Approximation for Data Influence](https://mlsanity.com/paper/2510.11832/) (2025)
- [Causally-Enhanced Reinforcement Policy Optimization](https://mlsanity.com/paper/2509.23095/) (2025)
- [An Isotropic Approach to Efficient Uncertainty Quantification with Gradient Norms](https://mlsanity.com/paper/2603.29466/) (2026)
- [DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution](https://mlsanity.com/paper/2606.18307/) (2026)
- [Divide and Predict: An Architecture for Input Space Partitioning and Enhanced Accuracy](https://mlsanity.com/paper/2603.08649/) (2026)
- [GradShield: Alignment Preserving Finetuning](https://mlsanity.com/paper/2605.14194/) (2026)
- [Validity Threats for Foundation Model Research](https://mlsanity.com/paper/2606.05029/) (2026)
- [Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution](https://mlsanity.com/paper/2606.13668/) (2026)
- [From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution](https://mlsanity.com/paper/2609.02771/) (2026)
- [Can Data Attribution Filter Out Subliminal Learning? Not Reliably](https://mlsanity.com/paper/2609.20027/) (2026)
- [Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution](https://mlsanity.com/paper/2609.31214/) (2026)

## Abstract (arXiv)

Influence functions are important for quantifying the impact of individual training data points on a model's predictions. Although extensive research has been conducted on influence functions in traditional machine learning models, their application to large language models (LLMs) has been limited. In this work, we conduct a systematic study to address a key question: do influence functions work on LLMs? Specifically, we evaluate influence functions across multiple tasks and find that they consistently perform poorly in most settings. Our further investigation reveals that their poor performance can be attributed to: (1) inevitable approximation errors when estimating the iHVP component due to the scale of LLMs, (2) uncertain convergence during fine-tuning, and, more fundamentally, (3) the definition itself, as changes in model parameters do not necessarily correlate with changes in LLM behavior. Thus, our study suggests the need for alternative approaches for identifying influential samples.