AdaSkip speeds up long-context LLM inference by adaptively skipping low-importance attention and FFN sublayers in both the prompt-reading and token-generation phases, with quality tradeoffs.
VCSUM: A Versatile Chinese Meeting Summarization Dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239 real-life meetings, with a total duration of over 230 hours. We claim our dataset is versatile because we provide the annotations of topic segmentation, headlines, segmentation summaries, overall meeting summaries, and salient sentences for each meeting transcript. As such, the dataset can adapt to various summarization tasks or methods, including segmentation-based summarization, multi-granularity summarization and retrieval-then-generate summarization. Our analysis confirms the effectiveness and robustness of VCSum. We also provide a set of benchmark models regarding different downstream summarization tasks on VCSum to facilitate further research. The dataset and code will be released at https://github.com/hahahawu/VCSum.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
AdaSkip speeds up long-context LLM inference by adaptively skipping low-importance attention and FFN sublayers in both the prompt-reading and token-generation phases, with quality tradeoffs.