Zobrazeno 1 - 10
of 6 436
pro vyhledávání: '"A. A. Eskin"'
Autor:
Chen, Justin Chih-Yao, Prasad, Archiki, Saha, Swarnadeep, Stengel-Eskin, Elias, Bansal, Mohit
Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. While these improve performance, they often reach a saturation point. Refinement offe
Externí odkaz:
http://arxiv.org/abs/2409.12147
Knowledge conflict arises from discrepancies between information in the context of a large language model (LLM) and the knowledge stored in its parameters. This can hurt performance when using standard decoding techniques, which tend to ignore the co
Externí odkaz:
http://arxiv.org/abs/2409.07394
Autor:
Saha, Swarnadeep, Prasad, Archiki, Chen, Justin Chih-Yao, Hase, Peter, Stengel-Eskin, Elias, Bansal, Mohit
Language models can be used to solve long-horizon planning problems in two distinct modes: a fast 'System-1' mode, directly generating plans without any explicit search or backtracking, and a slow 'System-2' mode, planning step-by-step by explicitly
Externí odkaz:
http://arxiv.org/abs/2407.14414
The model editing problem concerns how language models should learn new facts about the world over time. While empirical research on model editing has drawn widespread attention, the conceptual foundations of model editing remain shaky -- perhaps uns
Externí odkaz:
http://arxiv.org/abs/2406.19354
Vision-language models (VLMs) can respond to queries about images in many languages. However, beyond language, culture affects how we see things. For example, individuals from Western cultures focus more on the central figure in an image while indivi
Externí odkaz:
http://arxiv.org/abs/2406.11665
Do norms of rationality apply to machine learning models, in particular language models? In this paper we investigate this question by focusing on a special subset of rational norms: coherence norms. We consider both logical coherence norms as well a
Externí odkaz:
http://arxiv.org/abs/2406.03442
When answering questions, LLMs can convey not only an answer, but a level of confidence about the answer being correct. This includes explicit confidence markers (e.g. giving a numeric score) as well as implicit markers, like an authoritative tone or
Externí odkaz:
http://arxiv.org/abs/2405.21028
Autor:
Wang, Ziyang, Yu, Shoubin, Stengel-Eskin, Elias, Yoon, Jaehong, Cheng, Feng, Bertasius, Gedas, Bansal, Mohit
Video-language understanding tasks have focused on short video clips, often struggling with long-form video understanding tasks. Recently, many long video-language understanding approaches have leveraged the reasoning capabilities of Large Language M
Externí odkaz:
http://arxiv.org/abs/2405.19209
We revisit the theory of normal forms for non-uniformly contracting dynamics. We collect a number of lemmas and reformulations of the standard theory that will be used in other projects.
Externí odkaz:
http://arxiv.org/abs/2405.16208
While Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks, their substantial computational requirements and restricted number of calls constrain their practical utility, especially in long-horizon interac
Externí odkaz:
http://arxiv.org/abs/2405.02749