LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports

arXiv:2406.15809v5 Announce Type: replace Abstract: Citizen reporting platforms help the public and authorities stay informed about sexual harassment incidents. However, the high volume of data shared on these platforms makes reviewing each individual case challenging. Therefore, a summarization algorithm capable of processing and understanding various code-mixed languages is essential. In recent years, Large Language Models (LLMs) have shown exceptional performance in NLP tasks, including summarization. LLMs inherently produce abstractive summaries by paraphrasing the original text, while the generation of extractive summaries - selecting specific subsets from the original text - through LLMs remains largely unexplored. Moreover, LLMs have a limited context window size, restricting the amount of data that can be processed at once. We tackle these challenges by introducing LaMSUM, a novel multi-level framework combining summarization with different voting methods to generate extractive summaries for large collections of incident reports using LLMs. Extensive evaluation using four popular LLMs (Llama, Mistral, Claude and GPT-4o) demonstrates that LaMSUM outperforms state-of-the-art extractive summarization methods. Overall, this work represents one of the first attempts to achieve extractive summarization through LLMs, and is likely to support stakeholders by offering a comprehensive overview and enabling them to develop effective policies to minimize incidents of unwarranted harassment.

Related

• CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval
• Leveraging Large Language Models for Sarcastic Speech Annotation in Sarcasm Detection
• Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
• Mitigating LLM biases toward spurious social contexts using direct preference optimization

Source: arXiv cs.CL | 2026-04-20