90 citations · 332 across the 63 of their papers we have counts for
6 papers · 1 filter
Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
Sarah Ball, Niki Hasrati, Alexander Robey +4
Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input prompts, elicit disallowed cont…
On the Query Complexity of Verifier-Assisted Language Generation
Edoardo Botta, Yuchen Li, Aashay Mehta +3
Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade…
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta +5
Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inhe…
The Limitations of Limited Context for Constituency Parsing
Yuchen Li, Andrej Risteski
Incorporating syntax into neural approaches in NLP has a multitude of practical and scientific benefits. For instance, a language model that is syntax-aware is likely to be able to…
Extending and Improving Wordnet via Unsupervised Word Embeddings
Mikhail Khodak, Andrej Risteski, Christiane Fellbaum +1
This work presents an unsupervised approach for improving WordNet that builds upon recent advances in document and sense representation via distributional semantics. We apply our m…
Linear Algebraic Structure of Word Senses, with Applications to Polysemy
Sanjeev Arora, Yuanzhi Li, Yingyu Liang +2
Word embeddings are ubiquitous in NLP and information retrieval, but it is unclear what they represent when the word is polysemous. Here it is shown that multiple word senses resid…