paper-with-me

홈 › Papers

Language Model Cascades

2022-07-21 · David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-Dickstein, Kevin Murphy, Charles Sutton

Prompted models have demonstrated impressive few-shot learning abilities. Repeated interactions at test-time with a single model, or the composition of multiple models together, further expands capabilities. These compositions are probabilistic models, and may be expressed in the language of graphical models with random variables whose values are complex data types such as strings. Cases with control flow and dynamic structure require techniques from probabilistic programming, which allow implementing disparate model structures and inference strategies in a unified language. We formalize several existing techniques from this perspective, including scratchpads / chain of thought, verifiers, STaR, selection-inference, and tool use. We refer to the resulting programs as language model cascades.

📄 PDF Abstract BibTeX arXiv:2207.10342

Code (1)

google-research/cascades 공식 구현 jax

Tasks

Few-Shot LearningLanguage ModelingLanguage ModellingmodelProbabilistic Programming

Similar Papers 제목 키워드 기반

Faster Cascades via Speculative Decoding

2024-05-29 · Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Seungyeon Kim 외

Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: c…

On the Expressivity of Recurrent Neural Cascades with Identity

2024-05-19 · Nadezda Alexandrovna Knorozova, Alessandro Ronca

Recurrent Neural Cascades (RNC) are the class of recurrent neural networks with no cyclic dependencies among recurrent neurons. Their subclass RNC+ with positive recurrent weights has been shown to be closely connected t…

Predicting Diffusion Reach Probabilities via Representation Learning on Social Networks

2019-01-12 · Furkan Gursoy, Ahmet Onur Durahim

Diffusion reach probability between two nodes on a network is defined as the probability of a cascade originating from one node reaching to another node. An infinite number of cascades would enable calculation of true di…

Representation Learning

Simulating Hate Speech Cascades with Multi-LLM Agents: Empirical Grounding, Modeling Fidelity, and Intervention Strategies

2026-05-21 · Fan Huang arxiv

Faithful modeling of hateful content propagation on online platforms remains an open problem for moderation research. Classical cascade models that do not explicitly represent the profile, community, and content factors …

Multilingual Reasoning Cascades Need More Context

2026-06-25 · Arnav Mazumder, Dengjia Zhang, Shuyue Stella Li, Yulia Tsvetkov 외 arxiv

Translation cascades for reasoning translate the query from another language to English, reason in English, and translate the answer back to the original language. This is a competitive approach to multilingual reasoning…

Machine Translation