# DeepThink: Aligning Language Models with Domain-Specific User Intents

arXiv: https://arxiv.org/abs/2502.05497 · HTML: https://mlsanity.com/paper/2502.05497/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 8 Feb 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing](https://mlsanity.com/paper/2406.08464/) (2024)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [ChatQA: Surpassing GPT-4 on Conversational QA and RAG](https://mlsanity.com/paper/2401.10225/) (2024)
- [GPTEval: A Survey on Assessments of ChatGPT and GPT-4](https://mlsanity.com/paper/2308.12488/) (2023)
- [Synthetic Dialogue Dataset Generation using LLM Agents](https://mlsanity.com/paper/2401.17461/) (2024)
- [T-RAG: Lessons from the LLM Trenches](https://mlsanity.com/paper/2402.07483/) (2024)
- [CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues](https://mlsanity.com/paper/2404.03820/) (2024)
- [Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue](https://mlsanity.com/paper/2402.06967/) (2024)
- [Self-QA: Unsupervised Knowledge Guided Language Model Alignment](https://mlsanity.com/paper/2305.11952/) (2023)

## Built on by (most cited first, 2 of 2)

- [Role-Augmented Intent-Driven Generative Search Engine Optimization](https://mlsanity.com/paper/2508.11158/) (2025)
- [From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning](https://mlsanity.com/paper/2604.19516/) (2026)

## Abstract (arXiv)

Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. This study proposes a novel framework called DeepThink to generate high-quality instructions. DeepThink first generates a few seed questions to mimic actual user questions, simulates conversations to uncover the hidden user needs, and refines the answer by conversational contexts and the retrieved documents for more comprehensive answers. Experiments demonstrate that DeepThink achieves an average performance improvement of 7.92% compared to a GPT-4-turbo+RAG-based assistant on the real user test set in the advertising domain across dimensions such as relevance, completeness, clarity, accuracy, and actionability.