Search Results - "Levy, Mosh"

It's Easy to Beat the Market by Levy, Mosh

“…The perception that it's hard to beat the market portfolio is widespread. Indeed, passive investment has more than doubled in the last decade. While various…”
Get full text

Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature by Katz, Uri, Levy, Mosh, Goldberg, Yoav

“…The exponential growth of scientific literature necessitates advanced tools for effective knowledge exploration. We present Knowledge Navigator, a system…”
Get full text

Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models by Levy, Mosh, Jacoby, Alon, Goldberg, Yoav

“…This paper explores the impact of extending input lengths on the capabilities of Large Language Models (LLMs). Despite LLMs advancements in recent times, their…”
Get full text

Transpose Attack: Stealing Datasets with Bidirectional Training by Amit, Guy, Levy, Mosh, Mirsky, Yisroel

“…Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in…”
Get full text

Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers by Levy, Mosh, Ravfogel, Shauli, Goldberg, Yoav

“…Recent applications of LLMs in Machine Reading Comprehension (MRC) systems have shown impressive results, but the use of shortcuts, mechanisms triggered by…”
Get full text

Transferability Ranking of Adversarial Examples by Levy, Mosh, Amit, Guy, Elovici, Yuval, Mirsky, Yisroel

“…Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they…”
Get full text

Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models by Shapira, Natalie, Levy, Mosh, Alavi, Seyed Hossein, Zhou, Xuhui, Choi, Yejin, Goldberg, Yoav, Sap, Maarten, Shwartz, Vered

“…The escalating debate on AI's capabilities warrants developing reliable metrics to assess machine "intelligence". Recently, many anecdotal examples were used…”
Get full text