mlsanityData to 7 Oct 2026

Evolutionary Prompt Design for LLM-Based Post-ASR Error Correction

arXiv 2407.16370 ↗First posted 23 Jul 2024cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Building upon the strength of modern large language models (LLMs), generative error correction (GEC) has emerged as a promising paradigm that can elevate the performance of modern automatic speech recognition (ASR) systems. One representative approach is to leverage in-context learning to prompt LLMs so that a better hypothesis can be generated by the LLMs based on a carefully-designed prompt and an N-best list of hypotheses produced by ASR systems. However, it is yet unknown whether the existing prompts are the most effective ones for the task of post-ASR error correction. In this context, this paper first explores alternative prompts to identify an initial set of effective prompts, and then proposes to employ an evolutionary prompt optimization algorithm to refine the initial prompts. Evaluations results on the CHiME-4 subset of the Task 1 of the SLT 2024 GenSEC challenge show the effectiveness and potential of the proposed algorithms.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 23 Jul 2024.

Builds on

17 of 30 references.

References · 17

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  7. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  8. 2024Large Language Models: A Surveycited by 506
  9. 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
  10. 2023Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Promptingcited by 71
  11. 2023Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognitioncited by 56
  12. 2023N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Spacecited by 41
5 more
  1. 2023HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Modelscited by 41
  2. 2024Large Language Models are Efficient Learners of Noise-Robust Speech Recognitioncited by 30
  3. 2022WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Modelscited by 25
  4. 2020Multi-task Language Modeling for Improving Speech Recognition of Rare Wordscited by 21
  5. 2024Revisiting ASR Error Correction with Specialized Modelscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formulacited by 3
  2. 2025Listening, Imagining & Refining: A Heuristic Optimized ASR Correction Framework with LLMscited by 1
  3. 2025ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Featurescited by 0