mlsanityData to 14 Oct 2026

Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errors

arXiv 2406.17163 ↗First posted 24 Jun 2024cs.CL cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Large language models (LLM) have achieved remarkable success in natural language generation but lesser focus has been given to their applicability in decision making tasks such as classification. We show that LLMs like LLaMa can achieve high performance on large multi-class classification tasks but still make classification errors and worse, generate out-of-vocabulary class labels. To address these critical issues, we introduce Paraphrase and AGgregate (PAG)-LLM approach wherein an LLM generates multiple paraphrases of the input query (parallel queries), performs multi-class classification for the original query and each paraphrase, and at the end aggregate all the classification labels based on their confidence scores. We evaluate PAG-LLM on two large multi-class classication datasets: CLINC, and Banking and show 22.7% and 15.1% error reduction. We show that PAG-LLM is especially effective for hard examples where LLM is uncertain, and reduces the critical misclassification and hallucinated label generation errors

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 24 Jun 2024.

Builds on

18 of 29 references.

References · 18

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  8. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  9. 2019BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questionscited by 2,183
  10. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  11. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  12. 2020Efficient Intent Detection with Dual Sentence Encoderscited by 433
6 more
  1. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 386
  2. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 301
  3. 2021A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Modelscited by 101
  4. 2016A Thorough Examination of the CNN/Daily Mail Reading Comprehension Taskcited by 72
  5. 2023In-Context Learning for Text Classification with Many Labelscited by 35
  6. 2021Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLUcited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 5.

9 papers.

  1. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generationcited by 25
  2. 2025Fake News Detection After LLM Laundering: Measurement and Explanationcited by 4
  3. 2026Next Generation Active Learning: Mixture of LLMs in the Loopcited by 3
  4. 2025Smaller, Smarter, Closer: The Edge of Collaborative Generative AIcited by 2
  5. 2025Are LLMs Good Text Diacritizers? An Arabic and Yoruba Case Studycited by 2
  6. 2026Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verificationcited by 2
  7. 2026Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowdingcited by 1
  8. 2026Constrained Paraphrase Consistency for LLM Hallucination Detectioncited by 0
  9. 2026Test-Time Augmentation for LLMs: When Input Diversity Beats Output Diversity at Matched Computecited by 0