Search Results for author: Reid Pryzant

Found 19 papers, 6 papers with code

Prompt Engineering a Prompt Engineer

no code implementations9 Nov 2023 Qinyuan Ye, Maxamed Axmed, Reid Pryzant, Fereshte Khani

In addition, inspired by common optimization concepts such as batch size, step size and momentum, we introduce their verbalized counterparts to the meta-prompt and investigate their effects.

counterfactual Counterfactual Reasoning +2

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions

no code implementations19 Oct 2023 Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks.

Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization

no code implementations4 Oct 2023 Tanmay Gautam, Reid Pryzant, ZiYi Yang, Chenguang Zhu, Somayeh Sojoudi

SCQ works like a differentiable convex optimization (DCO) layer: in the forward pass, we solve for the optimal convex combination of codebook vectors that quantize the inputs.

Image Reconstruction Quantization

In-Context Demonstration Selection with Cross Entropy Difference

1 code implementation24 May 2023 Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu

Our method is based on the observation that the effectiveness of in-context demonstrations negatively correlates with the perplexity of the test example by a language model that was finetuned on that demonstration.

Language Modelling Test +1

i-Code Studio: A Configurable and Composable Framework for Integrative AI

no code implementations23 May 2023 Yuwei Fang, Mahmoud Khademi, Chenguang Zhu, ZiYi Yang, Reid Pryzant, Yichong Xu, Yao Qian, Takuya Yoshioka, Lu Yuan, Michael Zeng, Xuedong Huang

Artificial General Intelligence (AGI) requires comprehensive understanding and generation capabilities for a variety of tasks spanning different modalities and functionalities.

Question Answering Retrieval +4

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data

no code implementations21 May 2023 ZiYi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Mei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang

The convergence of text, visual, and audio data is a key step towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models which lack generative abilities.

Automatic Prompt Optimization with "Gradient Descent" and Beam Search

1 code implementation4 May 2023 Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, Michael Zeng

Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort.

APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning

no code implementations19 Dec 2022 Soumya Sanyal, Yichong Xu, Shuohang Wang, ZiYi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren

Logical reasoning of text is an important ability that requires understanding the information present in the text, their interconnections, and then reasoning through them to infer new conclusions.

Data Augmentation Language Modelling +2

Automatic Rule Induction for Interpretable Semi-Supervised Learning

1 code implementation18 May 2022 Reid Pryzant, ZiYi Yang, Yichong Xu, Chenguang Zhu, Michael Zeng

Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data.

Relation Extraction

Repairing Pronouns in Translation with BERT-Based Post-Editing

no code implementations23 Mar 2021 Reid Pryzant

We investigate the severity of this pronoun issue, showing that (1) in some domains, pronoun choice can account for more than half of a NMT systems' errors, and (2) pronouns have a disproportionately large impact on perceived translation quality.

Machine Translation NMT +1

Causal Effects of Linguistic Properties

1 code implementation NAACL 2021 Reid Pryzant, Dallas Card, Dan Jurafsky, Victor Veitch, Dhanya Sridhar

Second, in practice, we only have access to noisy proxies for the linguistic properties of interest -- e. g., predictions from classifiers and lexicons.

Language Modelling

Automatically Neutralizing Subjective Bias in Text

1 code implementation21 Nov 2019 Reid Pryzant, Richard Diehl Martinez, Nathan Dass, Sadao Kurohashi, Dan Jurafsky, Diyi Yang

To address this issue, we introduce a novel testbed for natural language generation: automatically bringing inappropriately subjective text into a neutral point of view ("neutralizing" biased text).

Text Generation

Deconfounded Lexicon Induction for Interpretable Social Science

no code implementations NAACL 2018 Reid Pryzant, Kelly Shen, Dan Jurafsky, Stefan Wagner

The first uses a bifurcated architecture to separate the explanatory power of the text and confounds.

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