mlsanityData to 14 Oct 2026

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

arXiv 2404.11055 ↗First posted 17 Apr 2024cs.CLcited by 2

Not on the map. Why?

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

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

6 of 25 references.

References · 6

  1. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  2. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  3. 2013Direct and Indirect Effectscited by 280
  4. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  5. 2021True Few-Shot Learning with Prompts -- A Real-World Perspectivecited by 38
  6. 2021Improving Document-Level Sentiment Classification Using Importance of Sentencescited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspectivecited by 25
  2. 2025LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probingcited by 15

Similar, not cited

Close in wording, no citation either way

  1. 2025Causal Prompting for Implicit Sentiment Analysis with Large Language Models
  2. 2026Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability
  3. 2025Disentangling Bias by Modeling Intra- and Inter-modal Causal Attention for Multimodal Sentiment Analysis
  4. 2024Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis
  5. 2026Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models
  6. 2026Causal methods for LLM development and evaluation
  7. 2026Can Post-Training Transform LLMs into Causal Reasoners?
  8. 2024RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals