# Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis

arXiv: https://arxiv.org/abs/2404.11055 · HTML: https://mlsanity.com/paper/2404.11055/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 6 of 6)

- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Towards the first adversarially robust neural network model on MNIST](https://mlsanity.com/paper/1805.09190/) (2018)
- [True Few-Shot Learning with Prompts -- A Real-World Perspective](https://mlsanity.com/paper/2111.13440/) (2021)
- [Improving Document-Level Sentiment Classification Using Importance of Sentences](https://mlsanity.com/paper/2103.05167/) (2021)

## Built on by (most cited first, 2 of 2)

- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing](https://mlsanity.com/paper/2505.16491/) (2025)

## Abstract (arXiv)

Sentiment analysis (SA) aims to identify the sentiment expressed in a text, such as a product review. Given a review and the sentiment associated with it, this work formulates SA as a combination of two tasks: (1) a causal discovery task that distinguishes whether a review "primes" the sentiment (Causal Hypothesis C1), or the sentiment "primes" the review (Causal Hypothesis C2); and (2) the traditional prediction task to model the sentiment using the review as input. Using the peak-end rule in psychology, we classify a sample as C1 if its overall sentiment score approximates an average of all the sentence-level sentiments in the review, and C2 if the overall sentiment score approximates an average of the peak and end sentiments. For the prediction task, we use the discovered causal mechanisms behind the samples to improve LLM performance by proposing causal prompts that give the models an inductive bias of the underlying causal graph, leading to substantial improvements by up to 32.13 F1 points on zero-shot five-class SA. Our code is at https://github.com/cogito233/causal-sa