mlsanityData to 7 Oct 2026

Self-Improving Customer Review Response Generation Based on LLMs

arXiv 2405.03845 ↗First posted 6 May 2024cs.CL cs.AIcited by 5

On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation

Abstract (arXiv)

Previous studies have demonstrated that proactive interaction with user reviews has a positive impact on the perception of app users and encourages them to submit revised ratings. Nevertheless, developers encounter challenges in managing a high volume of reviews, particularly in the case of popular apps with a substantial influx of daily reviews. Consequently, there is a demand for automated solutions aimed at streamlining the process of responding to user reviews. To address this, we have developed a new system for generating automatic responses by leveraging user-contributed documents with the help of retrieval-augmented generation (RAG) and advanced Large Language Models (LLMs). Our solution, named SCRABLE, represents an adaptive customer review response automation that enhances itself with self-optimizing prompts and a judging mechanism based on LLMs. Additionally, we introduce an automatic scoring mechanism that mimics the role of a human evaluator to assess the quality of responses generated in customer review domains. Extensive experiments and analyses conducted on real-world datasets reveal that our method is effective in producing high-quality responses, yielding improvement of more than 8.5% compared to the baseline. Further validation through manual examination of the generated responses underscores the efficacy our proposed system.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 52 of its 84 references that are in the map. First posted on arXiv 6 May 2024.

Builds on

52 of 84 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023The False Promise of Imitating Proprietary LLMs25 May

Other references · 51

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  7. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  8. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  9. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  10. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  11. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  12. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
38 more
  1. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  2. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  4. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  5. 2017Billion-scale similarity search with GPUscited by 2,477
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  7. 2023LIMA: Less Is More for Alignmentcited by 1,080
  8. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  9. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  10. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  11. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  12. 2023AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedbackcited by 738
  13. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 729
  14. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 724
  15. 2021BARTScore: Evaluating Generated Text as Text Generationcited by 719
  16. 2022A Survey on In-context Learningcited by 717
  17. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  18. 2023Automatic Prompt Optimization with "Gradient Descent" and Beam Searchcited by 628
  19. 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 558
  20. 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
  21. 2023How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resourcescited by 405
  22. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  23. 2023ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systemscited by 259
  24. 2023PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimizationcited by 226
  25. 2023Benchmarking Foundation Models with Language-Model-as-an-Examinercited by 172
  26. 2022Efficient Few-Shot Learning Without Promptscited by 135
  27. 2023Human-like Summarization Evaluation with ChatGPTcited by 126
  28. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 104
  29. 2023EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteriacited by 73
  30. 2023Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarizationcited by 70
  31. 2021Semantic Answer Similarity for Evaluating Question Answering Modelscited by 47
  32. 2022Efficient Few-Shot Fine-Tuning for Opinion Summarizationcited by 16
  33. 2020App-Aware Response Synthesis for User Reviewscited by 10
  34. 2020Automating App Review Response Generationcited by 8
  35. 2017Automatic Keyword Extraction for Text Summarization: A Surveycited by 7
  36. 2020Automating App Review Response Generation Based on Contextual Knowledgecited by 4
  37. 2022Pre-Trained Neural Language Models for Automatic Mobile App User Feedback Answer Generationcited by 2
  38. 2022A Transformer-Based Approach for Improving App Review Response Generationcited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Benchmarking and Learning Real-World Customer Service Dialoguecited by 1
  2. 2026Align Generative Artificial Intelligence with Human Preferences: A Novel Large Language Model Fine-Tuning Method for Online Review Managementcited by 1
  3. 2025PARAN: Persona-Augmented Review ANswering system on Food Delivery Review Datasetcited by 0
  4. 2026Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluationcited by 0
  5. 2026Enhancing LLMs through human feedback: a journey towards self-improvementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Rating Prediction with Off-the-Shelf LLMs Using In-Context User Reviews
  2. 2024Evaluating Quality of Answers for Retrieval-Augmented Generation: A Strong LLM Is All You Need
  3. 2025LLMs Can Generate a Better Answer by Aggregating Their Own Responses
  4. 2025Beyond Stars: Bridging the Gap Between Ratings and Review Sentiment with LLM
  5. 2025Can LLM feedback enhance review quality? A randomized study of 20K reviews at ICLR 2025
  6. 2026PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality
  7. 2024RAG based Question-Answering for Contextual Response Prediction System
  8. 2025Chatbot Arena Meets Nuggets: Towards Explanations and Diagnostics in the Evaluation of LLM Responses