Entity · paper

A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries

paperactiveprovisionala-human-in-the-loop-corpus-for-llm-based-simplification-of-scientific-summaries-d72c7762·1 events·first seen 2d ago

Aliases: A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries

Co-occurring entities

GPT-4o mini SciSummNet OpenAI

More like this (12)

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs Less is More: Quality-Aware Training Data Selection for Scientific Summarization human-LLM collaborative annotation clinical text summarization Learning to Summarize with Human Feedback Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics code synthesis LLMs A Komi-Yazva–Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translation LLM-augmented clinical NLP pipeline The Test Oracle Problem in Synthetic LLM-as-Judge Corpora: Disappearance, Distortion and a Validation Protocol Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges

Recent events (1)

3arXiv · cs.CL·2d ago·source ↗

Human-in-the-loop corpus for LLM-based simplification of scientific summaries released

Researchers present a two-phase human-in-the-loop workflow for simplifying scientific summaries using GPT-4o-mini, building on the SciSummNet corpus. Phase 1 collects comprehensibility judgments from non-specialist STEM readers, while Phase 2 has CS experts produce reference simplifications informed by that feedback. The resulting corpus with human judgments and automatic evaluation results is released to support training and benchmarking of scientific text simplification systems. Key findings include a preference for GPT-generated simplifications on comprehensibility and the importance of preserving domain-specific terminology.

Evaluation and Benchmarking GPT-4o mini A Human-in-the-Loop Corpus for LLM-Based Simplification of Scientific Summaries SciSummNet +1 more