Abstract: When a learning system is deployed, the data it encounters may no longer resemble its training data. The nature of this shift is typically unknown, whether due to changing conditions, adversarial manipulation, or simply a new deployment context. Without assumptions on the shift, reliable prediction is in general impossible, as the test distribution may…
Abstract: (The talk will be self-contained and no background on LLM Safety/Alignment is required.) This talk provides a foundational overview of recent efforts in industry and academia to improve the safety of frontier models, along with open challenges. It will cover (1) principal approaches to designing red-teaming attacks, (2) in-model and out-of-model methods for enhancing safety,…
Abstract: When faced with a small sample from a large universe of possible outcomes, scientists often turn to the venerable Good-Turing estimator. Despite its pedigree, however, this estimator comes with considerable drawbacks, such as the need to hand-tune smoothing parameters and the lack of a precise optimality guarantee. We introduce a tuning-parameter-free estimator that bests…
Abstract: When a learning system is deployed, the data it encounters may no longer resemble its training data. The nature of this shift is typically unknown, whether due to changing conditions, adversarial manipulation, or simply a new deployment context. Without assumptions on the shift, reliable prediction is in general impossible, as the test distribution may…
Abstract: (The talk will be self-contained and no background on LLM Safety/Alignment is required.) This talk provides a foundational overview of recent efforts in industry and academia to improve the safety of frontier models, along with open challenges. It will cover (1) principal approaches to designing red-teaming attacks, (2) in-model and out-of-model methods for enhancing safety,…
Abstract: When faced with a small sample from a large universe of possible outcomes, scientists often turn to the venerable Good-Turing estimator. Despite its pedigree, however, this estimator comes with considerable drawbacks, such as the need to hand-tune smoothing parameters and the lack of a precise optimality guarantee. We introduce a tuning-parameter-free estimator that bests…
TBD
