Paper Revision 2024.findings-emnlp.646, closes #4142.

data/xml/2024.findings.xml

@@ -28024,9 +28024,11 @@
       <author><first>Dit-Yan</first><last>Yeung</last><affiliation>Hong Kong University of Science and Technology</affiliation></author>
       <pages>11057-11070</pages>
       <abstract>Large Language Models (LLMs) have demonstrated impressive capabilities in a wide range of natural language processing tasks when leveraging in-context learning. To mitigate the additional computational and financial costs associated with in-context learning, several prompt compression methods have been proposed to compress the in-context learning prompts. Despite their success, these methods face challenges with transferability due to model-specific compression, or rely on external training data, such as GPT-4. In this paper, we investigate the ability of LLMs to develop a unified compression method that discretizes uninformative tokens, utilizing a self-supervised pre-training technique. By introducing a small number of parameters during the continual pre-training, the proposed Selection-p produces a probability for each input token, indicating whether to preserve or discard it. Experiments show Selection-p achieves state-of-the-art performance across numerous classification tasks, achieving compression rates of up to 10 times while experiencing only a marginal 0.8% decrease in performance. Moreover, it exhibits superior transferability to different models compared to prior work. Additionally, we further analyze how Selection-p helps maintain performance on in-context learning with long contexts.</abstract>
-      <url hash="80dc4135">2024.findings-emnlp.646</url>
+      <url hash="138885d0">2024.findings-emnlp.646</url>
       <bibkey>chung-etal-2024-selection</bibkey>
       <doi>10.18653/v1/2024.findings-emnlp.646</doi>
+      <revision id="1" href="2024.findings-emnlp.646v1" hash="80dc4135"/>
+      <revision id="2" href="2024.findings-emnlp.646v2" hash="138885d0" date="2024-12-11">Corrected email addresses.</revision>
     </paper>
     <paper id="647">
       <title>Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities</title>