Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotationsby Samyak Rawlekar, Shubhang Bhatnagar, Narendra AhujaFirst…
Fine-tuning Large Language Models for Entity Matchingby Aaron Steiner, Ralph Peeters, Christian BizerFirst submitted to…
Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilitiesby Thomas Ball,…
Beyond designer’s knowledge: Generating materials design hypotheses via large language modelsby Quanliang Liu, Maciej P.…
Residual Stream Analysis with Multi-Layer SAEsby Tim Lawson, Lucy Farnik, Conor Houghton, Laurence AitchisonFirst submitted…
Efficient and Scalable Estimation of Tool Representations in Vector Spaceby Suhong Moon, Siddharth Jha, Lutfi…
Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inferenceby Barys Liskavets, Maxim…
TinyAgent: Function Calling at the Edgeby Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha, Sehoon Kim,…
How Does Diverse Interpretability of Textual Prompts Impact Medical Vision-Language Zero-Shot Tasks?by Sicheng Wang, Che…
Data Augmentation for Image Classification using Generative AIby Fazle Rahat, M Shifat Hossain, Md Rubel…