GRIEF
发表于 2025-3-23 11:57:09
http://reply.papertrans.cn/83/8234/823394/823394_11.png
cumulative
发表于 2025-3-23 15:24:55
http://reply.papertrans.cn/83/8234/823394/823394_12.png
Ophthalmoscope
发表于 2025-3-23 18:43:19
Whether Large Language Models Learn at the Inference Stage? Effects of Active Learning and Labellingd recently, in connection with the discovered possibility of Large Language Models (LLMs) based on examples (and in particular demonstrations of instructions, some actions with examples, including demonstration of reasoning) to solve certain types of problems at the Inference stage, without the need
AGATE
发表于 2025-3-23 23:34:38
Machine Translation for Russian-Khakas Language Pair: Translation Results in Low-Resource Settingws that using the Russian-Chuvash language pair for pre-training can significantly improve the model’s performance. The study describes the process of collecting and preprocessing the data, tokenization, training and evaluation of the results.
surrogate
发表于 2025-3-24 05:46:34
http://reply.papertrans.cn/83/8234/823394/823394_15.png
委托
发表于 2025-3-24 07:02:11
http://reply.papertrans.cn/83/8234/823394/823394_16.png
Negotiate
发表于 2025-3-24 11:31:02
Tuning-Free Discriminative Nearest Neighbor Few-Shot Intent Detection via Consecutive Knowledge Tranenging because of limited data availability. In this study, we aim to develop a few-shot intent classification model capable of OOS detection that does not require fine-tuning on target data. We adopt the discriminative nearest neighbor classification architecture and replace the fine-tuning phase w
Jejune
发表于 2025-3-24 15:05:55
http://reply.papertrans.cn/83/8234/823394/823394_18.png
Postulate
发表于 2025-3-24 20:22:28
http://reply.papertrans.cn/83/8234/823394/823394_19.png
树胶
发表于 2025-3-25 01:58:47
http://reply.papertrans.cn/83/8234/823394/823394_20.png