9 citations · 30 across the 19 of their papers we have counts for
9 papers · 1 filter
Shared Global and Local Geometry of Language Model Embeddings
Andrew Lee, Melanie Weber, Fernanda Viégas +1
Researchers have recently suggested that models share common representations. In our work, we find numerous geometric similarities across the token embeddings of large language mod…
ICLR: In-Context Learning of Representations
Core Francisco Park, Andrew Lee, Ekdeep Singh Lubana +5
Recent work has demonstrated that semantics specified by pretraining data influence how representations of different concepts are organized in a large language model (LLM). However…
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
Andrew Lee, Xiaoyan Bai, Itamar Pres +3
While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which model…
Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss
Jing Xu, Andrew Lee, Sainbayar Sukhbaatar +1
Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input. Perhaps less…
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models
Oana Ignat, Zhijing Jin, Artem Abzaliev +19
Recent progress in large language models (LLMs) has enabled the deployment of many generative NLP applications. At the same time, it has also led to a misleading public discourse t…
Improving Chess Commentaries by Combining Language Models with Symbolic Reasoning Engines
Andrew Lee, David Wu, Emily Dinan +1
Despite many recent advancements in language modeling, state-of-the-art language models lack grounding in the real world and struggle with tasks involving complex reasoning. Meanwh…
Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health
Andrew Lee, Jonathan K. Kummerfeld, Lawrence C. An +1
Many statistical models have high accuracy on test benchmarks, but are not explainable, struggle in low-resource scenarios, cannot be reused for multiple tasks, and cannot easily i…
An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction
Stefan Larson, Anish Mahendran, Joseph J. Peper +8
Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover eve…
Outlier Detection for Improved Data Quality and Diversity in Dialog Systems
Stefan Larson, Anish Mahendran, Andrew Lee +6
In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outl…