no code implementations • NAACL (NUSE) 2021 • Louis Castricato, Stella Biderman, David Thue, Rogelio Cardona-Rivera
Our framework affords the ability to discuss key qualities of stories and their communication, including the flow of information from a Narrator to a Reader, the evolution of a Reader’s story model over time, and Reader uncertainty.
no code implementations • 8 Jan 2025 • Violet Xiang, Charlie Snell, Kanishk Gandhi, Alon Albalak, Anikait Singh, Chase Blagden, Duy Phung, Rafael Rafailov, Nathan Lile, Dakota Mahan, Louis Castricato, Jan-Philipp Franken, Nick Haber, Chelsea Finn
We propose a novel framework, Meta Chain-of-Thought (Meta-CoT), which extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive at a particular CoT.
no code implementations • 2 Oct 2024 • Dakota Mahan, Duy Van Phung, Rafael Rafailov, Chase Blagden, Nathan Lile, Louis Castricato, Jan-Philipp Fränken, Chelsea Finn, Alon Albalak
We introduce GenRM, an iterative algorithm that trains an LLM on self-generated reasoning traces, leading to synthetic preference labels matching human preference judgments.
no code implementations • 25 Jul 2024 • Nathan Lambert, Hailey Schoelkopf, Aaron Gokaslan, Luca Soldaini, Valentina Pyatkin, Louis Castricato
Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems.
no code implementations • 24 Jul 2024 • Louis Castricato, Nathan Lile, Rafael Rafailov, Jan-Philipp Fränken, Chelsea Finn
The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values.
no code implementations • 12 Feb 2024 • Louis Castricato, Nathan Lile, Suraj Anand, Hailey Schoelkopf, Siddharth Verma, Stella Biderman
Existing methods for controlling language models, such as RLHF and Constitutional AI, involve determining which LLM behaviors are desirable and training them into a language model.
no code implementations • 14 Oct 2022 • Louis Castricato, Alexander Havrilla, Shahbuland Matiana, Michael Pieler, Anbang Ye, Ian Yang, Spencer Frazier, Mark Riedl
However, simply fine-tuning a generative language model with a contrastive reward model does not always reliably result in a story generation system capable of generating stories that meet user preferences.
no code implementations • 12 Oct 2022 • Jason Phang, Herbie Bradley, Leo Gao, Louis Castricato, Stella Biderman
Over the past two years, EleutherAI has established itself as a radically novel initiative aimed at both promoting open-source research and conducting research in a transparent, openly accessible and collaborative manner.
2 code implementations • 30 Sep 2022 • Jack Merullo, Louis Castricato, Carsten Eickhoff, Ellie Pavlick
Prior work has shown that pretrained LMs can be taught to caption images when a vision model's parameters are optimized to encode images in the language space.
1 code implementation • 18 Apr 2022 • Katherine Crowson, Stella Biderman, Daniel Kornis, Dashiell Stander, Eric Hallahan, Louis Castricato, Edward Raff
Generating and editing images from open domain text prompts is a challenging task that heretofore has required expensive and specially trained models.
no code implementations • 7 Dec 2021 • Louis Castricato, Spencer Frazier, Jonathan Balloch, Nitya Tarakad, Mark Riedl
Neural language model-based approaches to automated story generation suffer from two important limitations.
no code implementations • 6 Oct 2021 • Shahbuland Matiana, JR Smith, Ryan Teehan, Louis Castricato, Stella Biderman, Leo Gao, Spencer Frazier
Recent advances in large-scale language models (Raffel et al., 2019; Brown et al., 2020) have brought significant qualitative and quantitative improvements in machine-driven text generation.
no code implementations • 1 Jun 2021 • Louis Castricato, Stephen Fitz, Won Young Shin
In this paper, we suggest that large language models are not necessary for good performance by showing a na\"{i}ve implementation of a GCN performs comparably to SoTA models based on pretrained language models.
no code implementations • NAACL (NUSE) 2021 • Louis Castricato, Spencer Frazier, Jonathan Balloch, Mark Riedl
Automated story generation remains a difficult area of research because it lacks strong objective measures.
no code implementations • 23 Mar 2021 • Louis Castricato, Stella Biderman, Rogelio E. Cardona-Rivera, David Thue
Our framework affords the ability to discuss key qualities of stories and their communication, including the flow of information from a Narrator to a Reader, the evolution of a Reader's story model over time, and Reader uncertainty.