Zobrazeno 1 - 10
of 203
pro vyhledávání: '"Wattenberg, Martin P."'
Autor:
Park, Core Francisco, Lee, Andrew, Lubana, Ekdeep Singh, Yang, Yongyi, Okawa, Maya, Nishi, Kento, Wattenberg, Martin, Tanaka, Hidenori
Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However, given the open-ended nature of LLMs, e.g., their ability to in-conte
Externí odkaz:
http://arxiv.org/abs/2501.00070
Many neural nets appear to represent data as linear combinations of "feature vectors." Algorithms for discovering these vectors have seen impressive recent success. However, we argue that this success is incomplete without an understanding of relatio
Externí odkaz:
http://arxiv.org/abs/2407.14662
Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner
We present an approach called Dialogue Action Tokens (DAT) that adapts language model agents to plan goal-directed dialogues. The core idea is to treat each utterance as an action, thereby converting dialogues into games where existing approaches suc
Externí odkaz:
http://arxiv.org/abs/2406.11978
Autor:
Chen, Yida, Wu, Aoyu, DePodesta, Trevor, Yeh, Catherine, Li, Kenneth, Marin, Nicholas Castillo, Patel, Oam, Riecke, Jan, Raval, Shivam, Seow, Olivia, Wattenberg, Martin, Viégas, Fernanda
Conversational LLMs function as black box systems, leaving users guessing about why they see the output they do. This lack of transparency is potentially problematic, especially given concerns around bias and truthfulness. To address this issue, we p
Externí odkaz:
http://arxiv.org/abs/2406.07882
Autor:
Li, Kenneth, Jelassi, Samy, Zhang, Hugh, Kakade, Sham, Wattenberg, Martin, Brandfonbrener, David
We present an approach called Q-probing to adapt a pre-trained language model to maximize a task-specific reward function. At a high level, Q-probing sits between heavier approaches such as finetuning and lighter approaches such as few shot prompting
Externí odkaz:
http://arxiv.org/abs/2402.14688
Autor:
Li, Kenneth, Liu, Tianle, Bashkansky, Naomi, Bau, David, Viégas, Fernanda, Pfister, Hanspeter, Wattenberg, Martin
System-prompting is a standard tool for customizing language-model chatbots, enabling them to follow a specific instruction. An implicit assumption in the use of system prompts is that they will be stable, so the chatbot will continue to generate tex
Externí odkaz:
http://arxiv.org/abs/2402.10962
Autor:
Lee, Andrew, Bai, Xiaoyan, Pres, Itamar, Wattenberg, Martin, Kummerfeld, Jonathan K., Mihalcea, Rada
While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain phenomena li
Externí odkaz:
http://arxiv.org/abs/2401.01967
Modern AI enables a high-level, declarative form of interaction: Users describe the intended outcome they wish an AI to produce, but do not actually create the outcome themselves. In contrast, in traditional user interfaces, users invoke specific ope
Externí odkaz:
http://arxiv.org/abs/2311.00710