2.8k citations
- University of TorontoCA238 papers
- Canadian Institute for Advanced ResearchCA56 papers
- University of WaterlooCA56 papers
- Perimeter InstituteCA27 papers
- Harvard UniversityUS25 papers
- Massachusetts Institute of TechnologyUS21 papers
- University of British ColumbiaCA17 papers
- ETH ZurichCH15 papers
- Stanford UniversityUS15 papers
- University Health NetworkCA14 papers
- National Research Council CanadaCA13 papers
- University of OttawaCA13 papers
16 papers · 1 filter
Test-Time Steering for Lossless Text Compression via Weighted Product of Experts
Qihang Zhang, Muchen Li, Ziao Wang +2
Lossless compression techniques are crucial in an era of rapidly growing data. Traditional universal compressors like gzip offer low computational overhead, high speed, and broad a…
Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
Linlu Qiu, Fei Sha, Kelsey Allen +3
Large language models (LLMs) are increasingly used as agents that interact with users and with the world. To do so successfully, LLMs must construct representations of the world an…
Blessing of Multilinguality: A Systematic Analysis of Multilingual In-Context Learning
Yilei Tu, Andrew Xue, Freda Shi
While multilingual large language models generally perform adequately, and sometimes even rival English performance on high-resource languages (HRLs), they often significantly unde…
The Mystery of the Pathological Path-star Task for Language Models
Arvid Frydenlund
The recently introduced path-star task is a minimal task designed to exemplify limitations to the abilities of language models (Bachmann and Nagarajan, 2024). It involves a path-st…
Decomposed Prompting to Answer Questions on a Course Discussion Board
Brandon Jaipersaud, Paul Zhang, Jimmy Ba +3
We propose and evaluate a question-answering system that uses decomposed prompting to classify and answer student questions on a course discussion board. Our system uses a large la…
Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model
Haikang Deng, Colin Raffel
While large language models have proven effective in a huge range of downstream applications, they often generate text that is problematic or lacks a desired attribute. In this pap…