mlsanityData to 14 Oct 2026

XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration

arXiv 2505.11336 ↗First posted 16 May 2025cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited in supporting high-quality scientific writing. Most existing systems are designed for general-purpose scientific text generation and fail to meet the sophisticated demands of research communication beyond surface-level polishing, for example, maintaining conceptual coherence across sections. Furthermore, academic writing is inherently iterative and revision-driven, a process that is not well supported by direct prompting-based paradigms. To address these scenarios, we propose a human-AI collaboration framework for academic paper revision, centered on criteria-guided intent alignment and context-aware modeling. To validate the framework, we curate a dataset of 7,000 research papers from top-tier venues, annotated with 140,000 instruction--response pairs that reflect realistic, section-level scientific revisions. We instantiate the framework in XtraGPT, the first suite of open-source LLMs (1.5B to 14B parameters) specifically fine-tuned for context-aware academic paper revision. Extensive experiments show that XtraGPT significantly outperforms same-scale baselines and rivals the quality of proprietary counterparts. Both automated preference assessments and human evaluations confirm the effectiveness of XtraGPT in improving scientific drafts. Our code and models are available at https://github.com/Xtra-Computing/XtraGPT and https://huggingface.co/collections/Xtra-Computing/xtragpt.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 59 of its 90 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

59 of 90 references.

References · 59

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  7. 2024GPT-4o System Cardcited by 4,588
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  9. 2023Qwen Technical Reportcited by 3,344
  10. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  11. 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
  12. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
38 more
  1. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  2. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 425
  3. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  4. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
  5. 2023Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvaturecited by 287
  6. 2024Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Textcited by 263
  7. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 245
  8. 2024ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Modelscited by 210
  9. 2023Can large language models provide useful feedback on research papers? A large-scale empirical analysiscited by 200
  10. 2023Does Writing with Language Models Reduce Content Diversity?cited by 192
  11. 2023Art or Artifice? Large Language Models and the False Promise of Creativitycited by 172
  12. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  13. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  14. 2023Benchmarking Cognitive Biases in Large Language Models as Evaluatorscited by 150
  15. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Researchcited by 149
  16. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 148
  17. 2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
  18. 2024MARG: Multi-Agent Review Generation for Scientific Paperscited by 104
  19. 2025DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Processcited by 100
  20. 2024Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agentscited by 97
  21. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoningcited by 94
  22. 2023AgentSims: An Open-Source Sandbox for Large Language Model Evaluationcited by 88
  23. 2023Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedbackcited by 78
  24. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
  25. 2024LitSearch: A Retrieval Benchmark for Scientific Literature Searchcited by 50
  26. 2024CiteME: Can Language Models Accurately Cite Scientific Claims?cited by 48
  27. 2024Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactionscited by 46
  28. 2024Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversationscited by 43
  29. 2019PaperRobot: Incremental Draft Generation of Scientific Ideascited by 37
  30. 2024AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agentscited by 37
  31. 2023CoQuest: Exploring Research Question Co-Creation with an LLM-based Agentcited by 34
  32. 2024Limited Ability of LLMs to Simulate Human Psychological Behaviours: a Psychometric Analysiscited by 31
  33. 2024CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Masterycited by 30
  34. 2023PlatoLM: Teaching LLMs in Multi-Round Dialogue via a User Simulatorcited by 29
  35. 2024SciLitLLM: How to Adapt LLMs for Scientific Literature Understandingcited by 29
  36. 2024Synthesizing Post-Training Data for LLMs through Multi-Agent Simulationcited by 24
  37. 2024MAIR: A Massive Benchmark for Evaluating Instructed Retrievalcited by 23
  38. 2024How AI Ideas Affect the Creativity, Diversity, and Evolution of Human Ideas: Evidence From a Large, Dynamic Experimentcited by 22

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  2. 2025A Call for Collaborative Intelligence: Why Human-Agent Systems Should Precede AI Autonomycited by 9
  3. 2026InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problemcited by 8
  4. 2026RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mindcited by 6
  5. 2026PaperJury: Due-Process Review for Bounded LaTeX Revisioncited by 1
  6. 2026The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishingcited by 1
  7. 2026Heterogeneous Element-Aware Cross-Version Differencing of Scientific Documents via Layout-Aware Alignment and Structure-Aware Reasoningcited by 0