State-of-the-art language generation models can degenerate when applied to open-ended generation problems such as text completion, story generation, or dialog modeling.
Along with text, these resources include visual content such as UI screenshots and images of application icons referenced in the text.
We then study various algorithms for improving from such feedback, including standard supervised learning, rejection sampling, model-guiding and reward-based learning, in order to make recommendations on which type of feedback and algorithms work best.
1 code implementation • 5 Aug 2022 • Kurt Shuster, Jing Xu, Mojtaba Komeili, Da Ju, Eric Michael Smith, Stephen Roller, Megan Ung, Moya Chen, Kushal Arora, Joshua Lane, Morteza Behrooz, William Ngan, Spencer Poff, Naman Goyal, Arthur Szlam, Y-Lan Boureau, Melanie Kambadur, Jason Weston
We present BlenderBot 3, a 175B parameter dialogue model capable of open-domain conversation with access to the internet and a long-term memory, and having been trained on a large number of user defined tasks.
Current language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness and contradictions.
Current language generation models suffer from issues such as repetition, incoherence, and hallucinations.
In this paper, we propose LexSub, a novel approach towards unifying lexical and distributional semantics.
In this paper, we address the last problem and propose a new discriminative entropy based intrinsic metric that works for both traditional word level models and unnormalized language models like sentence level models.