One Arrow, Many Targets: Probing LLMs for Multi-Attribute Controllable Text Summarization
This work addresses the limited exploration of multi-attribute controllable text summarization for NLP applications, representing an incremental advancement in the field.
The paper tackles the problem of Multi-Attribute Controllable Summarization (MACS) by using large language models with low-rank adapters and a hierarchical fusion technique, achieving results that demonstrate effectiveness in retaining multiple controllable attributes, though specific numerical gains are not provided.
Text summarization is a well-established task within the natural language processing (NLP) community. However, the focus on controllable summarization tailored to user requirements is gaining traction only recently. While several efforts explore controllability in text summarization, the investigation of Multi-Attribute Controllable Summarization (MACS) remains limited. This work addresses this gap by examining the MACS task through the lens of large language models (LLMs), using various learning paradigms, particularly low-rank adapters. We experiment with different popular adapter fine-tuning strategies to assess the effectiveness of the resulting models in retaining cues and patterns associated with multiple controllable attributes. Additionally, we propose and evaluate a novel hierarchical adapter fusion technique to integrate learnings from two distinct controllable attributes. Subsquently, we present our findings, discuss the challenges encountered, and suggest potential avenues for advancing the MACS task.