Tushar Khot

43 papers · 2015–2025 · 10 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (10) 🏃 Academic Marathon (10) 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (64) 🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (9) 🌟 Keyword Trendsetter Combo (4) 🤝 Dynamic Duo (36) 👑 Triple Crown 🏆 Grand Slam 👥 Mega-Team (43) 🔬 Deep Specialist (20) 🧬 Topic Evolution 🏆 Keyword Champion (3) ❓ The Questioner (6) 🗃️ Keyword Collector (160) ⚡ Prolific Year (6) 🔥 Unstoppable (11) 💎 Century Club (43) 📈 Trend Setter

Conferences

EMNLP (13) ACL (11) NAACL (6) ICLR (4) IJCNLP (3) NIPS (2) AAAI (1) CONLL (1) ICML (1) IJCAI (1)

Top co-authors

Ashish Sabharwal (36) Peter Clark (19) Daniel Khashabi (12) Hannaneh Hajishirzi (7) Kyle Richardson (7) Niranjan Balasubramanian (6) Harsh Trivedi (6) Pradeep Dasigi (4) Shashank Gupta (3) Bhavana Dalvi Mishra (3)

Keywords

question answering (13) multi-hop question answering (6) multi-hop reasoning (5) language model (5) large language model (4) knowledge retrieval (4) task decomposition (3) knowledge graph (3) agent system (3) reading comprehension (3) text representation (3) textual entailment (3) question decomposition (2) autonomous agent (2) data augmentation (2) natural language inference (2) transfer learning (2) retrieval-augmented generation (2) knowledge base (2) model evaluation (2)

Papers

DiscoveryBench: Towards Data-Driven Discovery with Large Language Models ICLR 2025

Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision NAACL 2025

ADaPT: As-Needed Decomposition and Planning with Language Models NAACL 2024

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs ICLR 2024

SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories EMNLP 2024

OLMo: Accelerating the Science of Language Models ACL 2024

AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents ACL 2024

DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents NIPS 2024

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources NIPS 2023

Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions ACL 2023

The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks ACL 2023

Decomposed Prompting: A Modular Approach for Solving Complex Tasks ICLR 2023

Complexity-Based Prompting for Multi-step Reasoning ICLR 2023

Specializing Smaller Language Models towards Multi-Step Reasoning ICML 2023

Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts EMNLP 2022

Hey AI, Can You Solve Complex Tasks by Talking to Agents? ACL 2022

Retrieval Data Augmentation Informed by Downstream Question Answering Performance ACL 2022

Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous Prompts NAACL 2022

Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? ACL 2021

GooAQ: Open Question Answering with Diverse Answer Types EMNLP 2021

ReadOnce Transformers: Reusable Representations of Text for Transformers ACL 2021

ReadOnce Transformers: Reusable Representations of Text for Transformers IJCNLP 2021

Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? IJCNLP 2021

Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models NAACL 2021

Temporal Reasoning on Implicit Events from Distant Supervision NAACL 2021

QASC: A Dataset for Question Answering via Sentence Composition AAAI 2020

IIRC: A Dataset of Incomplete Information Reading Comprehension Questions EMNLP 2020

UNIFIEDQA: Crossing Format Boundaries with a Single QA System EMNLP 2020

More Bang for Your Buck: Natural Perturbation for Robust Question Answering EMNLP 2020

Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning EMNLP 2020

UNQOVERing Stereotyping Biases via Underspecified Questions EMNLP 2020

A Simple Yet Strong Pipeline for HotpotQA EMNLP 2020

What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering IJCNLP 2019

What’s Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering EMNLP 2019

Exploiting Explicit Paths for Multi-hop Reading Comprehension ACL 2019

Repurposing Entailment for Multi-Hop Question Answering Tasks NAACL 2019

AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples ACL 2018

Bridging Knowledge Gaps in Neural Entailment via Symbolic Models EMNLP 2018

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering EMNLP 2018

Learning What is Essential in Questions CONLL 2017

Answering Complex Questions Using Open Information Extraction ACL 2017

Question Answering via Integer Programming over Semi-Structured Knowledge IJCAI 2016

Exploring Markov Logic Networks for Question Answering EMNLP 2015