565 citations · 2.3k across the 68 of their papers we have counts for
9 papers · 1 filter
Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability
Kyle Richardson, Ashish Sabharwal
Investigating the reasoning abilities of transformer models, and discovering new challenging tasks for them, has been a topic of much interest. Recent studies have found these mode…
Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts
Daniel Khashabi, Shane Lyu, Sewon Min +8
Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the fe…
Hey AI, Can You Solve Complex Tasks by Talking to Agents?
Tushar Khot, Kyle Richardson, Daniel Khashabi +1
Training giant models from scratch for each complex task is resource- and data-inefficient. To help develop models that can leverage existing systems, we propose a new challenge: L…
MuSiQue: Multihop Questions via Single-hop Question Composition
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot +1
Multihop reasoning remains an elusive goal as existing multihop benchmarks are known to be largely solvable via shortcuts. Can we create a question answering (QA) dataset that, by…
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?
Jieyu Zhao, Daniel Khashabi, Tushar Khot +2
Is it possible to use natural language to intervene in a model's behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventi…
Saturated Transformers are Constant-Depth Threshold Circuits
William Merrill, Ashish Sabharwal, Noah A. Smith
Transformers have become a standard neural network architecture for many NLP problems, motivating theoretical analysis of their power in terms of formal languages. Recent work has…