Zobrazeno 1 - 10
of 4 023
pro vyhledávání: '"Zick A"'
We study fair allocation of constrained resources, where a market designer optimizes overall welfare while maintaining group fairness. In many large-scale settings, utilities are not known in advance, but are instead observed after realizing the allo
Externí odkaz:
http://arxiv.org/abs/2411.02654
Autor:
Adler, Steven, Hitzig, Zoë, Jain, Shrey, Brewer, Catherine, Chang, Wayne, DiResta, Renée, Lazzarin, Eddy, McGregor, Sean, Seltzer, Wendy, Siddarth, Divya, Soliman, Nouran, South, Tobin, Spelliscy, Connor, Sporny, Manu, Srivastava, Varya, Bailey, John, Christian, Brian, Critch, Andrew, Falcon, Ronnie, Flanagan, Heather, Duffy, Kim Hamilton, Ho, Eric, Leibowicz, Claire R., Nadhamuni, Srikanth, Rozenshtein, Alan Z., Schnurr, David, Shapiro, Evan, Strahm, Lacey, Trask, Andrew, Weinberg, Zoe, Whitney, Cedric, Zick, Tom
Anonymity is an important principle online. However, malicious actors have long used misleading identities to conduct fraud, spread disinformation, and carry out other deceptive schemes. With the advent of increasingly capable AI, bad actors can ampl
Externí odkaz:
http://arxiv.org/abs/2408.07892
Numerous works propose post-hoc, model-agnostic explanations for learning to rank, focusing on ordering entities by their relevance to a query through feature attribution methods. However, these attributions often weakly correlate or contradict each
Externí odkaz:
http://arxiv.org/abs/2405.01848
Public sector use of AI has been quietly on the rise for the past decade, but only recently have efforts to regulate it entered the cultural zeitgeist. While simple to articulate, promoting ethical and effective roll outs of AI systems in government
Externí odkaz:
http://arxiv.org/abs/2404.14660
In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the \emph{percentile criterion}. The percentile criterion is approximately solved by constructing an \emph{ambigu
Externí odkaz:
http://arxiv.org/abs/2404.05055
Autor:
Lambert, Nathan, Pyatkin, Valentina, Morrison, Jacob, Miranda, LJ, Lin, Bill Yuchen, Chandu, Khyathi, Dziri, Nouha, Kumar, Sachin, Zick, Tom, Choi, Yejin, Smith, Noah A., Hajishirzi, Hannaneh
Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluation of those models. Evaluating reward models presents an opportunity to
Externí odkaz:
http://arxiv.org/abs/2403.13787
We study the problem of fair allocation of indivisible items when agents have ternary additive valuations -- each agent values each item at some fixed integer values $a$, $b$, or $c$ that are common to all agents. The notions of fairness we consider
Externí odkaz:
http://arxiv.org/abs/2403.00943
Autor:
Zick, Kenneth M.
Sparse Ising problems can be found in application areas such as logistics, condensed matter physics and training of deep Boltzmann networks, but can be very difficult to tackle with high efficiency and accuracy. This report presents new data demonstr
Externí odkaz:
http://arxiv.org/abs/2311.09275
Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) easier to use and more effective. A core piece of the RLHF process is the training and utilization of a model of human preferen
Externí odkaz:
http://arxiv.org/abs/2310.13595
The recent criticisms of the robustness of post hoc model approximation explanation methods (like LIME and SHAP) have led to the rise of model-precise abductive explanations. For each data point, abductive explanations provide a minimal subset of fea
Externí odkaz:
http://arxiv.org/abs/2310.03131