# Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification

arXiv: https://arxiv.org/abs/2503.15117 · HTML: https://mlsanity.com/paper/2503.15117/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [ChatGPT: Jack of all trades, master of none](https://mlsanity.com/paper/2302.10724/) (2023)
- [ReFT: Representation Finetuning for Language Models](https://mlsanity.com/paper/2404.03592/) (2024)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://mlsanity.com/paper/1512.01100/) (2015)
- [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023)
- [Aspect Based Sentiment Analysis with Gated Convolutional Networks](https://mlsanity.com/paper/1805.07043/) (2018)
- [Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification](https://mlsanity.com/paper/1909.06276/) (2019)

## Built on by (most cited first, 5 of 5)

- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)
- [Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2507.09485/) (2025)
- [Large Language Models Enhanced by Plug and Play Syntactic Knowledge for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2506.12991/) (2025)
- [In-Context Examples Matter: Improving Emotion Recognition in Conversation with Instruction Tuning](https://mlsanity.com/paper/2508.11889/) (2025)
- [PERCEIVE: A Benchmark for Personalized Emotion and Communication Behavior Understanding on Social Media](https://mlsanity.com/paper/2605.12525/) (2026)

## Abstract (arXiv)

Model editing aims at selectively updating a small subset of a neural model's parameters with an interpretable strategy to achieve desired modifications. It can significantly reduce computational costs to adapt to large language models (LLMs). Given its ability to precisely target critical components within LLMs, model editing shows great potential for efficient fine-tuning applications. In this work, we investigate model editing to serve an efficient method for adapting LLMs to solve aspect-based sentiment classification. Through causal interventions, we trace and determine which neuron hidden states are essential for the prediction of the model. By performing interventions and restorations on each component of an LLM, we identify the importance of these components for aspect-based sentiment classification. Our findings reveal that a distinct set of mid-layer representations is essential for detecting the sentiment polarity of given aspect words. Leveraging these insights, we develop a model editing approach that focuses exclusively on these critical parts of the LLM, leading to a more efficient method for adapting LLMs. Our in-domain and out-of-domain experiments demonstrate that this approach achieves competitive results compared to the currently strongest methods with significantly fewer trainable parameters, highlighting a more efficient and interpretable fine-tuning strategy.