REVIEW 7 cited by
Large language models for aspect-based sentiment analysis
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Large language models (LLMs) offer unprecedented text completion capabilities. As general models, they can fulfill a wide range of roles, including those of more specialized models. We assess the performance of GPT-4 and GPT-3.5 in zero shot, few shot and fine-tuned settings on the aspect-based sentiment analysis (ABSA) task. Fine-tuned GPT-3.5 achieves a state-of-the-art F1 score of 83.8 on the joint aspect term extraction and polarity classification task of the SemEval-2014 Task 4, improving upon InstructABSA [@scaria_instructabsa_2023] by 5.7%. However, this comes at the price of 1000 times more model parameters and thus increased inference cost. We discuss the the cost-performance trade-offs of different models, and analyze the typical errors that they make. Our results also indicate that detailed prompts improve performance in zero-shot and few-shot settings but are not necessary for fine-tuned models. This evidence is relevant for practioners that are faced with the choice of prompt engineering versus fine-tuning when using LLMs for ABSA.
Forward citations
Cited by 7 Pith papers
-
Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis
DPO-optimized LLM data augmentation with label balancing improves ABSA accuracy and F1 on most English benchmarks, but the balancing benefit is inconsistent.
-
Large Language Models Enhanced by Plug and Play Syntactic Knowledge for Aspect-based Sentiment Analysis
A memory-based plugin that encodes syntactic knowledge and is attached to a fixed LLM improves aspect-based sentiment analysis accuracy on standard benchmarks.
-
DS$^2$-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
DS2-ABSA combines key-point-driven and instance-driven LLM data synthesis with label normalization and noisy self-training to improve few-shot aspect-based sentiment analysis.
-
Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
Zero-shot LLMs, across nine models and five prompting strategies, underperform fine-tuned mBERT/XLM-R on multilingual aspect-based sentiment analysis, and simpler prompts generally outperform CoT, self-improvement, se...
-
A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis
Across 13 datasets and 8 ABSA subtasks, efficiently fine-tuned LLMs outperform cited fine-tuned SLM baselines, and retrieval-based demonstration selection improves in-context learning for API models.
-
Cross-lingual Aspect-Based Sentiment Analysis: A Survey on Tasks, Approaches, and Challenges
A comprehensive survey of cross-lingual aspect-based sentiment analysis that catalogs tasks, datasets, modeling paradigms, and cross-lingual transfer techniques, and identifies research gaps.
-
A Vision for Auto Research with LLM Agents
Proposes Agent-Based Auto Research, a multi-agent LLM pipeline covering the full research lifecycle, supported by preliminary qualitative and small-scale pilots.
Discussion (0). Continue with ORCID to comment.