Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis
This work addresses sentiment analysis for NLP researchers by providing a novel causal framework that enhances LLM accuracy, though it is incremental in applying causal methods to a specific domain.
The paper tackles sentiment analysis by formulating it as a causal discovery task to distinguish between two hypotheses about how reviews and sentiments interact, and uses this to improve LLM performance with causal prompts, achieving up to 32.13 F1 points gain in zero-shot five-class sentiment analysis.
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