Search Results for author:
Found 25 papers, 15 papers with code
Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizes
While matching or surpassing the performance of the transformer at sufficiently small dataset sizes and GBDTs at sufficiently large sizes, LLM-Boost and PFN-Boost outperform both standalone components on a wide range of dataset sizes in between.
Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking
In this work, we attempt to answer the following question -- do LLM-judge preferences translate to progress on other, more concrete metrics for alignment, and if not, why not?
LiveBench: A Challenging, Contamination-Limited LLM Benchmark
In this work, we introduce a new benchmark for LLMs designed to be resistant to both test set contamination and the pitfalls of LLM judging and human crowdsourcing.
Large Language Models Must Be Taught to Know What They Don't Know
We show that a thousand graded examples are sufficient to outperform baseline methods and that training through the features of a model is necessary for good performance and tractable for large open-source models when using LoRA.
Multi-objective Differentiable Neural Architecture Search
Pareto front profiling in multi-objective optimization (MOO), i. e. finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives like neural network training.
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
In this work, first we show theoretically that the standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.
ForecastPFN: Synthetically-Trained Zero-Shot Forecasting
The vast majority of time-series forecasting approaches require a substantial training dataset.
Fairer and More Accurate Tabular Models Through NAS
Making models algorithmically fairer in tabular data has been long studied, with techniques typically oriented towards fixes which usually take a neural model with an undesirable outcome and make changes to how the data are ingested, what the model weights are, or how outputs are processed.
Data Contamination Through the Lens of Time
Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks.
Giraffe: Adventures in Expanding Context Lengths in LLMs
To use these models on sequences longer than the train-time context length, one might employ techniques from the growing family of context length extrapolation methods -- most of which focus on modifying the system of positional encodings used in the attention mechanism to indicate where tokens or activations are located in the input sequence.
Robustness Disparities in Face Detection
Many existing algorithmic audits examine the performance of these systems on later stage elements of facial analysis systems like facial recognition and age, emotion, or perceived gender prediction; however, a core component to these systems has been vastly understudied from a fairness perspective: face detection, sometimes called face localization.
How Technology Impacts and Compares to Humans in Socially Consequential Arenas
As such, in this work, I make comparative analyses between humans and machines in three scenarios and seek to understand how sentiment about a technology, performance of that technology, and the impacts of that technology combine to influence how one decides to answer my main research question.
Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition
Our search outputs a suite of models which Pareto-dominate all other high-performance architectures and existing bias mitigation methods in terms of accuracy and fairness, often by large margins, on the two most widely used datasets for face identification, CelebA and VGGFace2.
A Deep Dive into Dataset Imbalance and Bias in Face Identification
This is an unfortunate omission, as 'imbalance' is a more complex matter in identification; imbalance may arise in not only the training data, but also the testing data, and furthermore may affect the proportion of identities belonging to each demographic group or the number of images belonging to each identity.
Topological Data Analysis for Word Sense Disambiguation
We develop and test a novel unsupervised algorithm for word sense induction and disambiguation which uses topological data analysis.
The Dichotomous Affiliate Stable Matching Problem: Approval-Based Matching with Applicant-Employer Relations
We also assume the agent's preferences over entire matchings are determined by a general weighted valuation function of their (and their affiliates') matches.
Are Commercial Face Detection Models as Biased as Academic Models?
When we compare the size of these disparities to that of commercial models, we conclude that commercial models - in contrast to their relatively larger development budget and industry-level fairness commitments - are always as biased or more biased than an academic model.
Comparing Human and Machine Bias in Face Recognition
Much recent research has uncovered and discussed serious concerns of bias in facial analysis technologies, finding performance disparities between groups of people based on perceived gender, skin type, lighting condition, etc.
Robustness Disparities in Commercial Face Detection
Facial detection and analysis systems have been deployed by large companies and critiqued by scholars and activists for the past decade.
PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning
In addition, we introduce a new metric to evaluate an auction allocations' adherence to such socially desirable constraints and demonstrate that our proposed method is competitive with current state-of-the-art neural-network based auction designs.
ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning
Inspired by these advances, in this paper, we extend techniques for approximating auctions using deep learning to address concerns of fairness while maintaining high revenue and strong incentive guarantees.
The Affiliate Matching Problem: On Labor Markets where Firms are Also Interested in the Placement of Previous Workers
We model this affiliate matching problem in a generalization of the classic stable marriage setting by permitting firms to state preferences over not just which workers to whom they are matched, but also to which firms their affiliated workers are matched.
Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
In this paper, we argue that traditional notions of fairness that are only based on models' outputs are not sufficient when the model is vulnerable to adversarial attacks.
Overhead Detection: Beyond 8-bits and RGB
Specifically, we examine how various features of the data affect building detection accuracy with respect to the Intersection over Union metric.
xView: Objects in Context in Overhead Imagery
We introduce a new large-scale dataset for the advancement of object detection techniques and overhead object detection research.
