21 citations · 96 across the 26 of their papers we have counts for
3 papers · 1 filter
LLM Explainability with Counterfactual Chains and Causal Graphs
Nirit Nussbaum-Hoffer, Nitay Calderon, Liat Ein-Dor +1
Causal graphs provide a high-level language for making mechanisms transparent. Recent work uses Large Language Models (LLMs) to recover causal graphs of external-world processes. I…
Stay Tuned: An Empirical Study of the Impact of Hyperparameters on LLM Tuning in Real-World Applications
Alon Halfon, Shai Gretz, Ofir Arviv +6
Fine-tuning Large Language Models (LLMs) is an effective method to enhance their performance on downstream tasks. However, choosing the appropriate setting of tuning hyperparameter…
Efficient Human Computation
Ran Gilad-Bachrach, Aharon Bar-Hillel, Liat Ein-Dor
Collecting large labeled data sets is a laborious and expensive task, whose scaling up requires division of the labeling workload between many teachers. When the number of classes…