Summary of Lamsum: Amplifying Voices Against Harassment Through Llm Guided Extractive Summarization Of User Incident Reports, by Garima Chhikara et al.
LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports
by Garima Chhikara, Anurag Sharma, V. Gurucharan, Kripabandhu Ghosh, Abhijnan Chakraborty
First submitted to arxiv on: 22 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 A novel framework called LaMSUM is introduced for generating extractive summaries from large collections of posts on Citizen reporting platforms like Safe City in India. These platforms help the public and authorities stay informed about sexual harassment incidents, but reviewing each individual case becomes challenging due to the high volume of data shared. Large Language Models (LLMs) have shown exceptional performance in NLP tasks, including summarization, and LaMSUM integrates summarization with different voting methods to achieve robust summaries using LLMs like Llama, Mistral, and GPT-4o. Evaluation demonstrates that LaMSUM outperforms state-of-the-art extractive summarization methods for Safe City posts, making it a significant contribution to the field of Natural Language Processing (NLP). The work has potential applications in enabling stakeholders to develop effective policies to minimize incidents of unwarranted harassment. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is being developed to help authorities review reports about sexual harassment on online platforms. These platforms get a lot of information, but it’s hard for people to look at each report individually. Large Language Models are computer programs that can understand and summarize text. A new method called LaMSUM uses these models to create summaries of the reports. The results show that LaMSUM does a better job than other methods of summarizing these reports. This could help authorities make sense of all the information and develop good policies to prevent harassment. |
Keywords
» Artificial intelligence » Gpt » Llama » Natural language processing » Nlp » Summarization
