Zobrazeno 1 - 10
of 330
pro vyhledávání: '"Cohen, William W."'
Autor:
Cohen, Cassandra A., Cohen, William W.
We propose a variant of chain of thought (CoT) prompting called Program Trace Prompting that makes explanations more observable while preserving the power, generality and flexibility of CoT. In our approach, few-shot CoT demonstrations are wrapped in
Externí odkaz:
http://arxiv.org/abs/2409.15359
Autor:
Sarch, Gabriel, Jang, Lawrence, Tarr, Michael J., Cohen, William W., Marino, Kenneth, Fragkiadaki, Katerina
Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot in-context learning for decision making and instruction following. However, they require high-quality exemplar demonstrations in their context window. In thi
Externí odkaz:
http://arxiv.org/abs/2406.14596
Autor:
Fisch, Adam, Maynez, Joshua, Hofer, R. Alex, Dhingra, Bhuwan, Globerson, Amir, Cohen, William W.
Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data. PPI achieves this by combining small amounts of human-labeled data with larger amounts of data labeled by a reasonably accurate --
Externí odkaz:
http://arxiv.org/abs/2406.04291
Autor:
Hofer, R. Alex, Maynez, Joshua, Dhingra, Bhuwan, Fisch, Adam, Globerson, Amir, Cohen, William W.
Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data. Specifically, PPI methods provide tighter confidence intervals by combining small amounts of human-labeled data with larger amount
Externí odkaz:
http://arxiv.org/abs/2405.06034
We propose a theoretical framework for formulating language model decoder algorithms with dynamic programming and information theory. With dynamic programming, we lift the design of decoder algorithms from the logit space to the action-state value fu
Externí odkaz:
http://arxiv.org/abs/2311.10083
Autor:
Bashlovkina, Vasilisa, Kuang, Zhaobin, Matthews, Riley, Clifford, Edward, Jun, Yennie, Cohen, William W., Baumgartner, Simon
Large language models (LLMs) are trained on web-scale corpora that inevitably include contradictory factual information from sources of varying reliability. In this paper, we propose measuring an LLM property called trusted source alignment (TSA): th
Externí odkaz:
http://arxiv.org/abs/2311.06697
Autor:
Schuster, Tal, Lelkes, Adam D., Sun, Haitian, Gupta, Jai, Berant, Jonathan, Cohen, William W., Metzler, Donald
Recently proposed long-form question answering (QA) systems, supported by large language models (LLMs), have shown promising capabilities. Yet, attributing and verifying their generated abstractive answers can be difficult, and automatically evaluati
Externí odkaz:
http://arxiv.org/abs/2311.04886
Autor:
Zemlyanskiy, Yury, de Jong, Michiel, Vilnis, Luke, Ontañón, Santiago, Cohen, William W., Sanghai, Sumit, Ainslie, Joshua
Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drastically speed up inference. However,
Externí odkaz:
http://arxiv.org/abs/2308.14903
Many open-domain questions are under-specified and thus have multiple possible answers, each of which is correct under a different interpretation of the question. Answering such ambiguous questions is challenging, as it requires retrieving and then r
Externí odkaz:
http://arxiv.org/abs/2308.08661
Autor:
de Jong, Michiel, Zemlyanskiy, Yury, FitzGerald, Nicholas, Sanghai, Sumit, Cohen, William W., Ainslie, Joshua
Memory-augmentation is a powerful approach for efficiently incorporating external information into language models, but leads to reduced performance relative to retrieving text. Recent work introduced LUMEN, a memory-retrieval hybrid that partially p
Externí odkaz:
http://arxiv.org/abs/2306.10231