Search Results for author: Louis Castricato

Found 15 papers, 2 papers with code

Towards a Model-Theoretic View of Narratives

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.

model

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though

no code implementations8 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.

Synthetic Data Generation

Generative Reward Models

no code implementations2 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.

reinforcement-learning Reinforcement Learning

Self-Directed Synthetic Dialogues and Revisions Technical Report

no code implementations25 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.

PERSONA: A Reproducible Testbed for Pluralistic Alignment

no code implementations24 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.

Suppressing Pink Elephants with Direct Principle Feedback

no code implementations12 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.

Language Modeling Language Modelling

Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning

no code implementations14 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.

Contrastive Learning Language Modeling +6

EleutherAI: Going Beyond "Open Science" to "Science in the Open"

no code implementations12 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.

Linearly Mapping from Image to Text Space

2 code implementations30 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.

Image Captioning Image to text +3

VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance

1 code implementation18 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.

Image Generation

Cut the CARP: Fishing for zero-shot story evaluation

no code implementations6 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.

Contrastive Learning Language Modeling +3

Parameter-Efficient Neural Question Answering Models via Graph-Enriched Document Representations

no code implementations1 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.

Question Answering

Towards a Formal Model of Narratives

no code implementations23 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.

model

Cannot find the paper you are looking for? You can Submit a new open access paper.