Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data Paper β’ 2404.05530 β’ Published Apr 8, 2024
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA Paper β’ 2208.09316 β’ Published Aug 19, 2022
UKP-SQUARE: An Online Platform for Question Answering Research Paper β’ 2203.13693 β’ Published Mar 25, 2022
UKP-SQuARE v3: A Platform for Multi-Agent QA Research Paper β’ 2303.18120 β’ Published Mar 31, 2023
Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking Paper β’ 2210.10695 β’ Published Oct 19, 2022
Scalable and Domain-General Abstractive Proposition Segmentation Paper β’ 2406.19803 β’ Published Jun 28, 2024 β’ 3
PeerQA: A Scientific Question Answering Dataset from Peer Reviews Paper β’ 2502.13668 β’ Published 22 days ago β’ 1
view post Post 617 I just got my first ChatGPT review on ARR! π Any advice on how to prove it's AI-generated? Thanks! See translation 3 replies Β· π§ 2 2 + Reply
view post Post 1470 I'm excited to announce that my internship paper at Parameter Lab was accepted to Findings of #NAACL2025 π TLDR: Stating an LLM was trained on a sentence might not be possible π₯ , but it is possible for large enough amounts of tokens, such as long documents or multiple documents! π€― Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models (2411.00154)π https://github.com/parameterlab/mia-scaling See translation π 4 4 π€ 2 2 π 1 1 + Reply
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models Paper β’ 2411.00154 β’ Published Oct 31, 2024