Mihir Parmar
18 papers · 2022–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Silver 🌍 Conference Polyglot · Bronze 🗺️ Taxonomy Completionist (47) 🤝 Dynamic Duo (15)
🤝
Dynamic Duo
(15)
❓
The Questioner
(3)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(85)
Venues
Top co-authors
Research topics
Artificial Intelligence
(14)
Core AI
(14)
Machine Learning
(11)
Natural Language Processing
(9)
Deep Learning
(8)
Learning Types · Machine Learning
(8)
Learning Types · Deep Learning
(6)
Resources & Methods
(6)
Application Areas
(4)
Applications
(3)
Generation
(3)
Learning Paradigms
(3)
Optimization & Theory
(3)
Computer Science
(1)
Knowledge & Reasoning
(1)
Keywords
large language model
(9)
logical reasoning
(4)
foundation model
(2)
error analysis
(2)
few-shot learning
(2)
question answering
(2)
supervised fine-tuning
(2)
benchmark evaluation
(2)
reasoning chain
(2)
reinforcement learning
(2)
text generation
(2)
propositional logic
(2)
natural language processing
(2)
instruction tuning
(2)
question decomposition
(1)
in-context learning
(1)
natural language inference
(1)
knowledge distillation
(1)
zero-shot learning
(1)
named entity recognition
(1)
Papers
CoAct: Co-Active LLM Preference Learning with Human-AI Synergy
ACL 2026
Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning
NAACL 2025
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
EMNLP 2025
PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
EMNLP 2025
ThinkTuning: Instilling Cognitive Reflections without Distillation
EMNLP 2025
EDM3: Event Detection as Multi-task Text Generation
NAACL 2024
Investigating Acceleration of LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with ‘LITE’
NAACL 2024
LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
ACL 2024
Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
EMNLP 2024
Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?
EMNLP 2024
Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs
EMNLP 2024
Don’t Blame the Annotator: Bias Already Starts in the Annotation Instructions
EACL 2023
How Many Data Samples is an Additional Instruction Worth?
EACL 2023
LogicAttack: Adversarial Attacks for Evaluating Logical Consistency of Natural Language Inference
EMNLP 2023
In-BoXBART: Get Instructions into Biomedical Multi-Task Learning
NAACL 2022
Is a Question Decomposition Unit All We Need?
EMNLP 2022
Less is More: Summary of Long Instructions is Better for Program Synthesis
EMNLP 2022
Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks
EMNLP 2022