168 citations · 711 across the 31 of their papers we have counts for
36 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
StoryScope: Investigating idiosyncrasies in AI fiction
Jenna Russell, Rishanth Rajendhran, Chau Minh Pham +2
As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in t…
Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data
Si Wu, John Wieting, David A. Smith
Unlike many other texts, literary works are often translated multiple times. We investigate strategies for leveraging these multi-reference datasets to improve literary machine tra…
PostMark: A Robust Blackbox Watermark for Large Language Models
Yapei Chang, Kalpesh Krishna, Amir Houmansadr +2
The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarki…
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Xinyi Wang, John Wieting, Jonathan H. Clark
Learning paradigms for large language models (LLMs) currently tend to fall within either in-context learning (ICL) or full fine-tuning. Each of these comes with their own trade-off…
XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages
Sebastian Ruder, Jonathan H. Clark, Alexander Gutkin +24
Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) -- languages for which NLP re-search is part…
Evaluating and Modeling Attribution for Cross-Lingual Question Answering
Benjamin Muller, John Wieting, Jonathan H. Clark +6
Trustworthy answer content is abundant in many high-resource languages and is instantly accessible through question answering systems, yet this content can be hard to access for th…
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, Orhan Firat +125
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…
A Gold Standard Dataset for the Reviewer Assignment Problem
Ivan Stelmakh, John Wieting, Sarina Xi +2
Many peer-review venues are using algorithms to assign submissions to reviewers. The crux of such automated approaches is the notion of the "similarity score" -- a numerical estima…
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Kalpesh Krishna, Yixiao Song, Marzena Karpinska +2
The rise in malicious usage of large language models, such as fake content creation and academic plagiarism, has motivated the development of approaches that identify AI-generated…
Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval
John Wieting, Jonathan H. Clark, William W. Cohen +2
Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In thi…
Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature
Katherine Thai, Marzena Karpinska, Kalpesh Krishna +4
Literary translation is a culturally significant task, but it is bottlenecked by the small number of qualified literary translators relative to the many untranslated works publishe…
QA Is the New KR: Question-Answer Pairs as Knowledge Bases
Wenhu Chen, William W. Cohen, Michiel De Jong +4
In this position paper, we propose a new approach to generating a type of knowledge base (KB) from text, based on question generation and entity linking. We argue that the proposed…
RankGen: Improving Text Generation with Large Ranking Models
Kalpesh Krishna, Yapei Chang, John Wieting +1
Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as suc…
Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization
Yue Dong, John Wieting, Pat Verga
Despite recent advances in abstractive summarization, current summarization systems still suffer from content hallucinations where models generate text that is either irrelevant or…
Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answering
Wenhu Chen, Pat Verga, Michiel de Jong +2
Retrieval augmented language models have recently become the standard for knowledge intensive tasks. Rather than relying purely on latent semantics within the parameters of large n…
Improving the Diversity of Unsupervised Paraphrasing with Embedding Outputs
Monisha Jegadeesan, Sachin Kumar, John Wieting +1
We present a novel technique for zero-shot paraphrase generation. The key contribution is an end-to-end multilingual paraphrasing model that is trained using translated parallel co…
On The Ingredients of an Effective Zero-shot Semantic Parser
Pengcheng Yin, John Wieting, Avirup Sil +1
Semantic parsers map natural language utterances into meaning representations (e.g., programs). Such models are typically bottlenecked by the paucity of training data due to the re…
Paraphrastic Representations at Scale
John Wieting, Kevin Gimpel, Graham Neubig +1
We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We also release trained models for Englis…
CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation
Jonathan H. Clark, Dan Garrette, Iulia Turc +1
Pipelined NLP systems have largely been superseded by end-to-end neural modeling, yet nearly all commonly-used models still require an explicit tokenization step. While recent toke…
Reformulating Unsupervised Style Transfer as Paraphrase Generation
Kalpesh Krishna, John Wieting, Mohit Iyyer
Modern NLP defines the task of style transfer as modifying the style of a given sentence without appreciably changing its semantics, which implies that the outputs of style transfe…
On Learning Text Style Transfer with Direct Rewards
Yixin Liu, Graham Neubig, John Wieting
In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task. In this paper, we explore training algorithms…
Improving Candidate Generation for Low-resource Cross-lingual Entity Linking
Shuyan Zhou, Shruti Rijhwani, John Wieting +2
Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts. The first step of (X…
A Bilingual Generative Transformer for Semantic Sentence Embedding
John Wieting, Graham Neubig, Taylor Berg-Kirkpatrick
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences…