Summary of Remodetect: Reward Models Recognize Aligned Llm’s Generations, by Hyunseok Lee et al.
ReMoDetect: Reward Models Recognize Aligned LLM’s Generationsby Hyunseok Lee, Jihoon Tack, Jinwoo ShinFirst submitted to…
ReMoDetect: Reward Models Recognize Aligned LLM’s Generationsby Hyunseok Lee, Jihoon Tack, Jinwoo ShinFirst submitted to…
Efficient multi-prompt evaluation of LLMsby Felipe Maia Polo, Ronald Xu, Lucas Weber, Mírian Silva, Onkar…
Mixture of Latent Experts Using Tensor Productsby Zhan Su, Fengran Mo, Prayag Tiwari, Benyou Wang,…
KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledgeby Pengcheng Jiang, Lang Cao, Cao Xiao, Parminder Bhatia,…
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplarsby Zhaoxuan Wu, Xiaoqiang Lin, Zhongxiang…
Theoretical Analysis of Weak-to-Strong Generalizationby Hunter Lang, David Sontag, Aravindan VijayaraghavanFirst submitted to arxiv on:…
BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detectionby Yuwei Niu, Shuo He, Qi Wei, Zongyu Wu,…
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognitionby Zijin Gu, Tatiana…
In-context Time Series Predictorby Jiecheng Lu, Yan Sun, Shihao YangFirst submitted to arxiv on: 23…
Extracting Prompts by Inverting LLM Outputsby Collin Zhang, John X. Morris, Vitaly ShmatikovFirst submitted to…