Alicia Parrish and colleagues, 2021
We introduce the Bias Benchmark for QA (BBQ), a dataset of question sets constructed by the authors that highlight attested social biases.
Don't Just Read it – Explore It
We introduce the Bias Benchmark for QA (BBQ), a dataset of question sets constructed by the authors that highlight attested social biases.
In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds.
We present StereoSet, a large-scale natural dataset in English to measure stereotypical biases in four domains: gender, profession, race, and religion.
To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench).
We introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC design.
We introduce Chatbot Arena, an open platform for evaluating LLMs based on human preferences.
To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions.
The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians.
We propose complexity-based prompting, a simple and effective example selection scheme for multi-step reasoning.
We propose Demonstrate-Search-Predict, a framework that relies on passing natural language texts in sophisticated pipelines between an LM and an RM.
RAP repurposes the LLM as both a world model and a reasoning agent.
To help close this gap, we introduce Minerva, a large language model pretrained on general natural language data and further trained on technical content.