Fetching the paper…
Reading the bibliography…
Even after fine-tuning and reinforcement learning, large language models (LLMs) can be difficult, if not impossible, to control reliably with prompts alone.
On-line inference for hidden markov models via particle filters
Paul Fearnhead and Peter Clifford · 2003
Earlier work this paper cites.
Feynman-kac formulae
Pierre Del Moral · 2004
Earlier work this paper cites.
Diverse beam search: Decoding diverse solutions from neural sequence models
Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R Selvaraju, Qing Sun, Stefan Lee, David Crandall, and Dhruv Batra · 2016
Earlier work this paper cites.
Correcting length bias in neural machine translation
Kenton Murray and David Chiang · 2018
Earlier work this paper cites.
Gen: a general-purpose probabilistic programming system with programmable inference
Marco F Cusumano-Towner, Feras A Saad, Alexander K Lew, and Vikash K Mansinghka · 2019
Earlier work this paper cites.
Plug and play language models: A simple approach to controlled text generation
Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu · 2019
Earlier work this paper cites.
CGMH: Constrained sentence generation by metropolis-hastings sampling
Ning Miao, Hao Zhou, Lili Mou, Rui Yan, and Lei Li · 2019
Earlier work this paper cites.
Enabling language models to fill in the blanks
Chris Donahue, Mina Lee, and Percy Liang · 2020
Earlier work this paper cites.
Leveraging unstructured statistical knowledge in a probabilistic language of thought
Alexander K Lew, Michael Henry Tessler, Vikash K Mansinghka, and Joshua B Tenenbaum · 2020
Earlier work this paper cites.
If beam search is the answer, what was the question?
Clara Meister, Tim Vieira, and Ryan Cotterell · 2020
Earlier work this paper cites.
Directed beam search: Plug-and-play lexically constrained language generation
Damian Pascual, Beni Egressy, Florian Bolli, and Roger Wattenhofer · 2020
Earlier work this paper cites.
Maosen Zhang, Nan Jiang, Lei Li, and Yexiang Xue · 2020
Earlier work this paper cites.
A distributional approach to controlled text generation
Muhammad Khalifa, Hady Elsahar, and Marc Dymetman · 2021
Cited alongside, same era.
Controlled text generation as continuous optimization with multiple constraints
Sachin Kumar, Eric Malmi, Aliaksei Severyn, and Yulia Tsvetkov · 2021
Cited alongside, same era.
Neurologic A* esque decoding: Constrained text generation with lookahead heuristics
Ximing Lu, Sean Welleck, Peter West, Liwei Jiang, Jungo Kasai, Daniel Khashabi, Ronan Le Bras, Lianhui Qin, Youngjae Yu, Rowan Zellers, et al · 2021
Cited alongside, same era.
Efficient training of language models to fill in the middle
Mohammad Bavarian, Heewoo Jun, Nikolas Tezak, John Schulman, Christine McLeavey, Jerry Tworek, and Mark Chen · 2022
Cited alongside, same era.
Prompting is programming: A query language for large language models
Flexible generation from fragmentary linguistic input
Peng Qian and Roger Levy · 2022
Later among the works it cites.
COLD decoding: Energy-based constrained text generation with Langevin dynamics
Lianhui Qin, Sean Welleck, Daniel Khashabi, and Yejin Choi · 2022
Later among the works it cites.
Most language models can be poets too: An ai writing assistant and constrained text generation studio
Allen Roush, Sanjay Basu, Akshay Moorthy, and Dmitry Dubovoy · 2022
Later among the works it cites.
Chain of thought prompting elicits reasoning in large language models
Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed H. Chi, Quoc V Le, and Denny Zhou · 2022
Later among the works it cites.
GenGPT3.jl: GPT-3 as a generative function in Gen.jl, November 2022
Tan Zhi-Xuan · 2022
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Luca Beurer-Kellner, Marc Fischer, and Martin Vechev · 2022
Cited alongside, same era.
David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A Saurous, Jascha Sohl-Dickstein, et al · 2022
Cited alongside, same era.
A high-level programming language for generative protein design
Brian Hie, Salvatore Candido, Zeming Lin, Ori Kabeli, Roshan Rao, Nikita Smetanin, Tom Sercu, and Alexander Rives · 2022
Cited alongside, same era.
RL with KL penalties is better viewed as Bayesian inference
Tomasz Korbak, Ethan Perez, and Christopher Buckley · 2022
Cited alongside, same era.
Constrained sampling from language models via Langevin dynamics in embedding spaces
Sachin Kumar, Biswajit Paria, and Yulia Tsvetkov · 2022
Cited alongside, same era.
Recursive monte carlo and variational inference with auxiliary variables
Alexander K Lew, Marco Cusumano-Towner, and Vikash K Mansinghka · 2022
Cited alongside, same era.
Training language models to follow instructions with human feedback
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al · 2022
Cited alongside, same era.
Synchromesh: Reliable code generation from pre-trained language models
Gabriel Poesia, Oleksandr Polozov, Vu Le, Ashish Tiwari, Gustavo Soares, Christopher Meek, and Sumit Gulwani · 2022
Cited alongside, same era.
Probabilistic programming with stochastic probabilities
Alexander K Lew, Matin Ghavamizadeh, Martin Rinard, and Vikash K Mansinghka · 2023
Closest in time.
Lampp: Language models as probabilistic priors for perception and action
Belinda Z Li, William Chen, Pratyusha Sharma, and Jacob Andreas · 2023
Closest in time.
Guidance: A guidance language for controlling large language models., 2023
Microsoft and Scott Lundberg · 2023
Closest in time.
Outlines: Generative model programming, May 2023
Normal Computing and Remi Louf · 2023
Closest in time.
Direct preference optimization: Your language model is secretly a reward model
Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D Manning, and Chelsea Finn · 2023
Closest in time.
Llama: Open and efficient foundation language models
Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al · 2023
Closest in time.
Large language models are human-level prompt engineers
Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba · 2023
Closest in time.