mlsanityData to 7 Oct 2026

LLM-Friendly Knowledge Representation for Customer Support

arXiv 2510.10331 ↗First posted 11 Oct 2025cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

We propose a practical approach by integrating Large Language Models (LLMs) with a framework designed to navigate the complexities of Airbnb customer support operations. In this paper, our methodology employs a novel reformatting technique, the Intent, Context, and Action (ICA) format, which transforms policies and workflows into a structure more comprehensible to LLMs. Additionally, we develop a synthetic data generation strategy to create training data with minimal human intervention, enabling cost-effective fine-tuning of our model. Our internal experiments (not applied to Airbnb products) demonstrate that our approach of restructuring workflows and fine-tuning LLMs with synthetic data significantly enhances their performance, setting a new benchmark for their application in customer support. Our solution is not only cost-effective but also improves customer support, as evidenced by both accuracy and manual processing time evaluation metrics.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 11 Oct 2025.

Builds on

14 of 27 references.

References · 14

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  4. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  5. 2022Large Language Models Can Self-Improvecited by 656
  6. 2019Revisiting Self-Training for Neural Sequence Generationcited by 154
  7. 2023Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answeringcited by 119
  8. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  9. 2024Best Practices and Lessons Learned on Synthetic Datacited by 104
  10. 2023RewriteLM: An Instruction-Tuned Large Language Model for Text Rewritingcited by 67
  11. 2020Parallel Data Augmentation for Formality Style Transfercited by 39
  12. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 39
2 more
  1. 2022EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Startcited by 35
  2. 2020Unsupervised Paraphrasing via Deep Reinforcement Learningcited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026Asymmetric Actor-Critic for Multi-turn LLM Agentscited by 4
  2. 2026Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Frameworkcited by 3
  3. 2026Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-Improvementcited by 1
  4. 2026Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMscited by 0
  5. 2026Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generationcited by 0
  6. 2026Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steeringcited by 0
  7. 2026Learning Selective LLM Autonomy from Copilot Feedback in Enterprise Customer Support Workflowscited by 0
  8. 2026Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Textscited by 0
  9. 2026POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systemscited by 0
  10. 2026RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agentscited by 0
  11. 2026Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scalecited by 0