22 citations · 56 across the 17 of their papers we have counts for
18 papers
Frontier AI performance across the business disciplines: a case-grounded benchmark of knowledge work and analytical reasoning
Ajay Patel, Kartik Hosanagar, Ramayya Krishnan +2
Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as factual recall, narrow question answe…
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale
Ajay Patel, Colin Raffel, Chris Callison-Burch
Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstruct…
mStyleDistance: Multilingual Style Embeddings and their Evaluation
Justin Qiu, Jiacheng Zhu, Ajay Patel +2
Style embeddings are useful for stylistic analysis and style transfer; however, only English style embeddings have been made available. We introduce Multilingual StyleDistance (mSt…
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
Yue Yang, Ajay Patel, Matt Deitke +8
Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due t…
StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples
Ajay Patel, Jiacheng Zhu, Justin Qiu +4
Style representations aim to embed texts with similar writing styles closely and texts with different styles far apart, regardless of content. However, the contrastive triplets oft…
Latent Space Interpretation for Stylistic Analysis and Explainable Authorship Attribution
Milad Alshomary, Narutatsu Ri, Marianna Apidianaki +3
Recent state-of-the-art authorship attribution methods learn authorship representations of texts in a latent, non-interpretable space, hindering their usability in real-world appli…
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
Matt Deitke, Christopher Clark, Sangho Lee +47
Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good perfor…
TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
Zachary Horvitz, Ajay Patel, Kanishk Singh +3
The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style. Existing style trans…
Large Language Models Can Self-Improve At Web Agent Tasks
Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei +3
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of tr…
DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows
Ajay Patel, Colin Raffel, Chris Callison-Burch
Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation,…
ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer
Zachary Horvitz, Ajay Patel, Chris Callison-Burch +2
Textual style transfer is the task of transforming stylistic properties of text while preserving meaning. Target "styles" can be defined in numerous ways, ranging from single attri…
Leveraging Large Language Models in Conversational Recommender Systems
Luke Friedman, Sameer Ahuja, David Allen +10
A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Rec…
Learning Interpretable Style Embeddings via Prompting LLMs
Ajay Patel, Delip Rao, Ansh Kothary +2
Style representation learning builds content-independent representations of author style in text. Stylometry, the analysis of style in text, is often performed by expert forensic l…
Low-Resource Authorship Style Transfer: Can Non-Famous Authors Be Imitated?
Ajay Patel, Nicholas Andrews, Chris Callison-Burch
Authorship style transfer involves altering text to match the style of a target author whilst preserving the original meaning. Existing unsupervised approaches like STRAP have larg…
Bidirectional Language Models Are Also Few-shot Learners
Ajay Patel, Bryan Li, Mohammad Sadegh Rasooli +3
Large language models such as GPT-3 (Brown et al., 2020) can perform arbitrary tasks without undergoing fine-tuning after being prompted with only a few labeled examples. An arbitr…
Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation
Bryan Li, Mohammad Sadegh Rasooli, Ajay Patel +1
We propose a two-stage approach for training a single NMT model to translate unseen languages both to and from English. For the first stage, we initialize an encoder-decoder model…
Magnitude: A Fast, Efficient Universal Vector Embedding Utility Package
Ajay Patel, Alexander Sands, Chris Callison-Burch +1
Vector space embedding models like word2vec, GloVe, fastText, and ELMo are extremely popular representations in natural language processing (NLP) applications. We present Magnitude…