Ashish Sabharwal
15 papers in the PaperMetrix corpus
Papers by this author
-
Exploring Markov Logic Networks for Question Answering
2015
Elementary-level science exams pose sig-nificant knowledge acquisition and rea-soning challenges for automatic question answering. We develop a system that rea-sons with knowledge derived from text-books, represented in a subset of first-order logic. Automatic extraction, while …
-
Knowledge Completion for Generics using Guided Tensor Factorization
2018 · Transactions of the Association for Computational Linguistics
Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as “all trees produce oxygen” or “some animals live in forests”, we consider the problem of inferring additional such facts …
-
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs
2022 · arXiv (Cornell University)
Can we teach natural language understanding models to track their beliefs through intermediate points in text? We propose a representation learning framework called breakpoint modeling that allows for learning of this type. Given any text …
-
ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
2025 · arXiv (Cornell University)
We investigate the logical reasoning capabilities of large language models (LLMs) and their scalability in complex non-monotonic reasoning. To this end, we introduce ZebraLogic, a comprehensive evaluation framework for assessing LLM reasoning performance on logic …
-
Parsing Algebraic Word Problems into Equations
2015 · Transactions of the Association for Computational Linguistics
This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees and score their likelihood by learning local …
-
Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions
2016 · Proceedings of the AAAI Conference on Artificial Intelligence
What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test …
-
SciTaiL: A Textual Entailment Dataset from Science Question Answering
2018 · Proceedings of the AAAI Conference on Artificial Intelligence
We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem. SciTail is the first entailment set that is created solely from natural sentences that already exist …
-
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
2018 · arXiv (Cornell University)
We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. Together, these constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning …
-
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
2018
We present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. The open book that comes with our questions is a set of 1326 …
-
AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples
2018
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large lexical resources in …
-
QUAREL: A Dataset and Models for Answering Questions about Qualitative Relationships
2019
Many natural la guage questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with corpus-based methods. Qualitative modeling provides tools that support such reasoning, but …
-
QASC: A Dataset for Question Answering via Sentence Composition
2020
Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus …
-
Probing Natural Language Inference Models through Semantic Fragments
2020
Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word substitutions in sentential contexts)? While such phenomena …
-
Complexity-Based Prompting for Multi-Step Reasoning
2022 · arXiv (Cornell University)
We study the task of prompting large-scale language models to perform multi-step reasoning. Existing work shows that when prompted with a chain of thoughts (CoT), sequences of short sentences describing intermediate reasoning steps towards a …
-
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions
2023
Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge is either unavailable to the LLM …