Reid Pryzant


2024

pdf bib
i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data
Ziyi Yang | Mahmoud Khademi | Yichong Xu | Reid Pryzant | Yuwei Fang | Chenguang Zhu | Dongdong Chen | Yao Qian | Xuemei Gao | Yi-Ling Chen | Robert Gmyr | Naoyuki Kanda | Noel Codella | Bin Xiao | Yu Shi | Lu Yuan | Takuya Yoshioka | Michael Zeng | Xuedong Huang
Findings of the Association for Computational Linguistics: NAACL 2024

The convergence of text, visual, and audio data is crucial towards human-like artificial intelligence, however the current Vision-Language-Speech landscape is dominated by encoder-only models that lack generative abilities. We propose closing this gap with i-Code V2, one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data. i-Code V2 leverages state-of-the-art single-modality encoders, combining their outputs with a new modality-fusing encoder to project combinations of modalities into a shared representational space. Language tokens are generated from these representations via an autoregressive decoder. i-Code V2 is pretrained end-to-end on a large collection of dual- and single-modality datasets with a novel text completion objective that can be generalized across arbitrary combinations of modalities. i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks, demonstrating the power of generative multimodal pretraining across a diversity of tasks and signals.

pdf bib
Prompt Engineering a Prompt Engineer
Qinyuan Ye | Mohamed Ahmed | Reid Pryzant | Fereshte Khani
Findings of the Association for Computational Linguistics ACL 2024

Prompt engineering is a challenging yet crucial task for optimizing the performance of large language models on customized tasks. It requires complex reasoning to examine the model’s errors, hypothesize what is missing or misleading in the current prompt, and communicate the task with clarity. While recent works indicate that large language models can be meta-prompted to perform automatic prompt engineering, we argue that their potential is limited due to insufficient guidance for complex reasoning in the meta-prompt. We fill this gap by infusing into the meta-prompt three key components: detailed descriptions, context specification, and a step-by-step reasoning template. The resulting method, named PE2, showcases remarkable versatility across diverse language tasks. It finds prompts that outperform “let’s think step by step” by 6.3% on MultiArith and 3.1% on GSM8K, and outperforms competitive baselines on counterfactual tasks by 6.9%. Further, we show that PE2 can make targeted prompt edits, rectify erroneous prompts, and induce multi-step plans for complex tasks.

2023

pdf bib
APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
Soumya Sanyal | Yichong Xu | Shuohang Wang | Ziyi Yang | Reid Pryzant | Wenhao Yu | Chenguang Zhu | Xiang Ren
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Logical reasoning over text is an important ability that requires understanding the semantics of the text and reasoning through them to arrive at correct inferences. Prior works on pretraining language models to improve the logical reasoning ability require complex processing of training data (e.g., aligning symbolic knowledge to text), yielding task-specific data augmentation that is not easy to adapt to any general text corpus. In this work, we propose APOLLO, a simple adaptive pretraining approach to improve the logical reasoning skills of language models. We select a subset of Wikipedia for adaptive pretraining using a set of logical inference keywords as filter words. Further, we propose two self-supervised loss functions for training. First, we modify the masked language modeling loss only to mask specific parts-of-speech words that likely require higher-order reasoning to predict them. Second, we propose a sentence-level classification loss that teaches the model to distinguish between entailment and contradiction types of sentences. The proposed pretraining paradigm is both simple and independent of task formats. We demonstrate the effectiveness of APOLLO by comparing it with prior baselines on two logical reasoning datasets. APOLLO performs comparably on ReClor and outperforms baselines on LogiQA.

pdf bib
In-Context Demonstration Selection with Cross Entropy Difference
Dan Iter | Reid Pryzant | Ruochen Xu | Shuohang Wang | Yang Liu | Yichong Xu | Chenguang Zhu
Findings of the Association for Computational Linguistics: EMNLP 2023

Large language models (LLMs) can use in-context demonstrations to improve performance on zero-shot tasks. However, selecting the best in-context examples is challenging because model performance can vary widely depending on the selected examples. We present a cross-entropy difference (CED) method for selecting in-context demonstrations. 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. We utilize parameter efficient finetuning to train small models on training data that are used for computing the cross-entropy difference between a test example and every candidate in-context demonstration. This metric is used to rank and select in-context demonstrations independently for each test input. We evaluate our method on a mix-domain dataset that combines 8 benchmarks, representing 4 text generation tasks, showing that CED for in-context demonstration selection can improve performance for a variety of LLMs over baseline selection methods.

pdf bib
The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
Siru Ouyang | Shuohang Wang | Yang Liu | Ming Zhong | Yizhu Jiao | Dan Iter | Reid Pryzant | Chenguang Zhu | Heng Ji | Jiawei Han
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks. However, it remains unclear whether the existing focus of NLP research accurately captures the genuine requirements of human users. This paper provides a comprehensive analysis of the divergence between academic research in NLP and the needs of real-world NLP applications via a large-scale collection of user-GPT conversations. We analyze a large-scale collection of real user queries to GPT. We compare these queries against existing NLP benchmark tasks and identify a significant gap between the tasks that users frequently request from LLMs and the tasks that are commonly studied in academic research. For example, we find that tasks such as “design” and “planning” are prevalent in user interactions but largely neglected or different from traditional NLP benchmarks. We investigate these overlooked tasks, dissect the practical challenges, and provide insights toward a roadmap to make LLMs better aligned with user needs.

pdf bib
Automatic Prompt Optimization with “Gradient Descent” and Beam Search
Reid Pryzant | Dan Iter | Jerry Li | Yin Lee | Chenguang Zhu | Michael Zeng
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

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. We propose a simple and nonparametric solution to this problem, Prompt Optimization with Textual Gradients (ProTeGi), which is inspired by numerical gradient descent to automatically improve prompts, assuming access to training data and an LLM API. The algorithm uses minibatches of data to form natural language “gradients” that criticize the current prompt, much like how numerical gradients point in the direction of error ascent. The natural language gradients are then “propagated” into the prompt by editing the prompt in the opposite semantic direction of the gradient. These gradient descent steps are guided by a beam search and bandit selection procedure which significantly improves algorithmic efficiency. Preliminary results across three benchmark NLP tasks and the novel problem of LLM jailbreak detection suggest that Automatic Prompt Optimization can outperform prior prompt editing techniques and improve an initial prompt’s performance by up to 31%, by using data to rewrite vague task descriptions into more precise annotation instructions.

2022

pdf bib
Automatic Rule Induction for Efficient Semi-Supervised Learning
Reid Pryzant | Ziyi Yang | Yichong Xu | Chenguang Zhu | Michael Zeng
Findings of the Association for Computational Linguistics: EMNLP 2022

Semi-supervised learning has shown promise in allowing NLP models to generalize from small amounts of labeled data. Meanwhile, pretrained transformer models act as black-box correlation engines that are difficult to explain and sometimes behave unreliably. In this paper, we propose tackling both of these challenges via Automatic Rule Induction (ARI), a simple and general-purpose framework for the automatic discovery and integration of symbolic rules into pretrained transformer models. First, we extract weak symbolic rules from low-capacity machine learning models trained on small amounts of labeled data. Next, we use an attention mechanism to integrate these rules into high-capacity pretrained transformer models. Last, the rule-augmented system becomes part of a self-training framework to boost supervision signal on unlabeled data. These steps can be layered beneath a variety of existing weak supervision and semi-supervised NLP algorithms in order to improve performance and interpretability. Experiments across nine sequence classification and relation extraction tasks suggest that ARI can improve state-of-the-art methods with no manual effort and minimal computational overhead.

pdf bib
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
Amir Feder | Katherine A. Keith | Emaad Manzoor | Reid Pryzant | Dhanya Sridhar | Zach Wood-Doughty | Jacob Eisenstein | Justin Grimmer | Roi Reichart | Margaret E. Roberts | Brandon M. Stewart | Victor Veitch | Diyi Yang
Transactions of the Association for Computational Linguistics, Volume 10

A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has traditionally placed more emphasis on predictive tasks. This distinction is beginning to fade, with an emerging area of interdisciplinary research at the convergence of causal inference and language processing. Still, research on causality in NLP remains scattered across domains without unified definitions, benchmark datasets and clear articulations of the challenges and opportunities in the application of causal inference to the textual domain, with its unique properties. In this survey, we consolidate research across academic areas and situate it in the broader NLP landscape. We introduce the statistical challenge of estimating causal effects with text, encompassing settings where text is used as an outcome, treatment, or to address confounding. In addition, we explore potential uses of causal inference to improve the robustness, fairness, and interpretability of NLP models. We thus provide a unified overview of causal inference for the NLP community.1

2021

pdf bib
Causal Effects of Linguistic Properties
Reid Pryzant | Dallas Card | Dan Jurafsky | Victor Veitch | Dhanya Sridhar
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

We consider the problem of using observational data to estimate the causal effects of linguistic properties. For example, does writing a complaint politely lead to a faster response time? How much will a positive product review increase sales? This paper addresses two technical challenges related to the problem before developing a practical method. First, we formalize the causal quantity of interest as the effect of a writer’s intent, and establish the assumptions necessary to identify this from observational data. Second, in practice, we only have access to noisy proxies for the linguistic properties of interest—e.g., predictions from classifiers and lexicons. We propose an estimator for this setting and prove that its bias is bounded when we perform an adjustment for the text. Based on these results, we introduce TextCause, an algorithm for estimating causal effects of linguistic properties. The method leverages (1) distant supervision to improve the quality of noisy proxies, and (2) a pre-trained language model (BERT) to adjust for the text. We show that the proposed method outperforms related approaches when estimating the effect of Amazon review sentiment on semi-simulated sales figures. Finally, we present an applied case study investigating the effects of complaint politeness on bureaucratic response times.

pdf bib
Proceedings of the First Workshop on Causal Inference and NLP
Amir Feder | Katherine Keith | Emaad Manzoor | Reid Pryzant | Dhanya Sridhar | Zach Wood-Doughty | Jacob Eisenstein | Justin Grimmer | Roi Reichart | Molly Roberts | Uri Shalit | Brandon Stewart | Victor Veitch | Diyi Yang
Proceedings of the First Workshop on Causal Inference and NLP

2018

pdf bib
Deconfounded Lexicon Induction for Interpretable Social Science
Reid Pryzant | Kelly Shen | Dan Jurafsky | Stefan Wagner
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

NLP algorithms are increasingly used in computational social science to take linguistic observations and predict outcomes like human preferences or actions. Making these social models transparent and interpretable often requires identifying features in the input that predict outcomes while also controlling for potential confounds. We formalize this need as a new task: inducing a lexicon that is predictive of a set of target variables yet uncorrelated to a set of confounding variables. We introduce two deep learning algorithms for the task. The first uses a bifurcated architecture to separate the explanatory power of the text and confounds. The second uses an adversarial discriminator to force confound-invariant text encodings. Both elicit lexicons from learned weights and attentional scores. We use them to induce lexicons that are predictive of timely responses to consumer complaints (controlling for product), enrollment from course descriptions (controlling for subject), and sales from product descriptions (controlling for seller). In each domain our algorithms pick words that are associated with narrative persuasion; more predictive and less confound-related than those of standard feature weighting and lexicon induction techniques like regression and log odds.

pdf bib
JESC: Japanese-English Subtitle Corpus
Reid Pryzant | Youngjoo Chung | Dan Jurafsky | Denny Britz
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Interpretable Neural Architectures for Attributing an Ad’s Performance to its Writing Style
Reid Pryzant | Sugato Basu | Kazoo Sone
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

How much does “free shipping!” help an advertisement’s ability to persuade? This paper presents two methods for performance attribution: finding the degree to which an outcome can be attributed to parts of a text while controlling for potential confounders. Both algorithms are based on interpreting the behaviors and parameters of trained neural networks. One method uses a CNN to encode the text, an adversarial objective function to control for confounders, and projects its weights onto its activations to interpret the importance of each phrase towards each output class. The other method leverages residualization to control for confounds and performs interpretation by aggregating over learned word vectors. We demonstrate these algorithms’ efficacy on 118,000 internet search advertisements and outcomes, finding language indicative of high and low click through rate (CTR) regardless of who the ad is by or what it is for. Our results suggest the proposed algorithms are high performance and data efficient, able to glean actionable insights from fewer than 10,000 data points. We find that quick, easy, and authoritative language is associated with success, while lackluster embellishment is related to failure. These findings agree with the advertising industry’s emperical wisdom, automatically revealing insights which previously required manual A/B testing to discover.

2017

pdf bib
Effective Domain Mixing for Neural Machine Translation
Denny Britz | Quoc Le | Reid Pryzant
Proceedings of the Second Conference on Machine Translation