Summary of Learning to Verify Summary Facts with Fine-grained Llm Feedback, by Jihwan Oh et al.
Learning to Verify Summary Facts with Fine-Grained LLM Feedback
by Jihwan Oh, Jeonghwan Choi, Nicole Hee-Yeon Kim, Taewon Yun, Hwanjun Song
First submitted to arxiv on: 14 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces FineSumFact, a large-scale dataset containing fine-grained factual feedback on summaries. The authors employ 10 distinct Large Language Models (LLMs) for diverse summary generation and Llama-3-70B-Instruct for feedback. They utilize this dataset to fine-tune the lightweight open-source model Llama-3-8B-Instruct, optimizing resource efficiency while maintaining high performance. Experimental results reveal that the model trained on extensive LLM-generated datasets surpasses that trained on smaller human-annotated datasets when evaluated using human-generated test sets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a way to make machines better at checking if summaries are true or not. They use computers to generate lots of different summaries and then ask them what’s correct or not. This helps the machine learning model get better without needing as much help from humans. The results show that this method works well and could be useful in the future. |
Keywords
» Artificial intelligence » Llama » Machine learning
