BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases Paper • 2505.20321 • Published 14 days ago • 5
The Trickle-down Impact of Reward (In-)consistency on RLHF Paper • 2309.16155 • Published Sep 28, 2023
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project Paper • 1909.01958 • Published Sep 4, 2019
Revisiting the Hypothesis: Do pretrained Transformers Learn In-Context by Gradient Descent? Paper • 2310.08540 • Published Oct 12, 2023
Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency Paper • 2305.10713 • Published May 18, 2023
UnifiedQA: Crossing Format Boundaries With a Single QA System Paper • 2005.00700 • Published May 2, 2020
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models Paper • 2009.00751 • Published Sep 1, 2020
ParsiNLU: A Suite of Language Understanding Challenges for Persian Paper • 2012.06154 • Published Dec 11, 2020
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies Paper • 2101.02235 • Published Jan 6, 2021
Cross-Task Generalization via Natural Language Crowdsourcing Instructions Paper • 2104.08773 • Published Apr 18, 2021
GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution Paper • 2307.08775 • Published Jul 17, 2023 • 1
Hey AI, Can You Solve Complex Tasks by Talking to Agents? Paper • 2110.08542 • Published Oct 16, 2021
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts Paper • 2112.08348 • Published Dec 15, 2021
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics Paper • 2112.08726 • Published Dec 16, 2021
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics Paper • 2202.11705 • Published Feb 23, 2022
AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies Paper • 2402.12370 • Published Feb 19, 2024 • 2
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks Paper • 2204.07705 • Published Apr 16, 2022 • 1
ProsocialDialog: A Prosocial Backbone for Conversational Agents Paper • 2205.12688 • Published May 25, 2022