Towards AI-Assisted Research Writing: Benchmarking LLMs for AI/ML Introduction Generation

arXiv:2508.14273 · cs.CL · Submitted 2025-08-19 · Read on arXiv

cs.CL

Submitted: 2025-08-19

Updated: 2026-08-31

Code: https://github.com/danielnsilva/semanticscholar

Terminology

• Consistency — 41× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 26× in this paper · explained in 3 episodes
• Semantic Similarity — 14× in this paper · explained in 2 episodes
• Alignment — 12× in this paper · explained in 1 episode
• Natural Language Processing — 10× in this paper
• Perplexity — 10× in this paper · explained in 3 episodes
• Aggregation — 9× in this paper · explained in 1 episode
• Multi-Document Summarization — 6× in this paper
• Benchmarking — 5× in this paper · explained in 3 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Hallucination — 5× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 5× in this paper · explained in 6 episodes
• Reference-based Coverage — 4× in this paper
• Reference-free Coverage — 4× in this paper
• Ablation — 3× in this paper · explained in 1 episode
• Ablation study — 3× in this paper · explained in 1 episode
• Core — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 3× in this paper
• Self-consistency — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Domain Adaptation — 2× in this paper · explained in 5 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Structured Prompting — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• GPT-4o System Card
• The Semantic Scholar Open Data Platform
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
• DeepSeek-V3 Technical Report
• G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
• Gemma 3 Technical Report
• LLaMA: Open and Efficient Foundation Language Models
• AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering