AIConfPaper
← Search

Mihir Parmar

18 accepted papers

2026

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

Minbeom Kim, Mihir Parmar, Phillip Wallis, Lesly Miculicich, Kyomin Jung, Krishnamurthy Dvijotham +2
ICML 2026poster

AI agents equipped with tool-calling capabilities are susceptible to *Indirect Prompt Injection* (IPI) attacks. In this attack scenario, malicious commands hidden within *untrusted* content trick the agent into performing unauthorized actions. Existing defenses can reduce attack success but often su…

Cited by 0Source ↗Scholar ↗
2026

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time

Divij Handa, Mihir Parmar, Aswin RRV, Md Nayem Uddin, Hamid Palangi, Chitta Baral
ICLR 2026poster

Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often struggles to generate diverse solution candidates, frequently relying on the same underlying approach to…

Cited by 0Source ↗code ↗Scholar ↗
2026

TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems

Md Atik Ahamed, Mihir Parmar, Palash Goyal, Yiwen Song, Long T. Le, Qiang (Shaun) Cheng +4
ICML 2026poster

We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as "black boxes." Unlike existing benchmarks, TFRBench provides a prot…

Cited by 0Source ↗Scholar ↗
2025

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning

Venkatesh Mishra, Bimsara Pathiraja, Mihir Parmar, Sat Chidananda, Jayanth Srinivasa, Gaowen Liu +2
NAACL 2025findings

Reasoning abilities of LLMs have been a key focus in recent years. One challenging reasoning domain with interesting nuances is legal reasoning, which requires careful application of rules, and precedents while balancing deductive and analogical reasoning, and conflicts between rules. Although there…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving

Mihir Parmar, Palash Goyal, Xin Liu, Yiwen Song, Mingyang Ling, Chitta Baral +2
EMNLP 2025

Recently, decomposing complex problems into simple subtasks–a crucial part of human-like natural planning–to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such planning structures during post-training to boost the performance o

Cited by 0Source ↗PDF ↗Scholar ↗
2025

PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving

Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra +8
EMNLP 2025

Recent agent frameworks and inference-time algorithms often struggle with natural planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification with

Cited by 0Source ↗PDF ↗Scholar ↗
2025

ThinkTuning: Instilling Cognitive Reflections without Distillation

Aswin Rrv, Jacob Dineen, Divij Handa, Md Nayem Uddin, Mihir Parmar, Chitta Baral +1
EMNLP 2025

Recent advances in test-time scaling have led to the emergence of thinking LLMs that exhibit self-reflective behaviors and multi-step reasoning. While RL drives this self-improvement paradigm, recent studies show that solely RL does not truly instill these new reasoning abilities - it merely draws o

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Investigating Acceleration of LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with ‘LITE’

Neeraj Varshney, Agneet Chatterjee, Mihir Parmar, Chitta Baral
NAACL 2024findings

Large Language Models (LLMs) have achieved remarkable performance across a wide variety of tasks; however, their large size makes their inference slow and computationally expensive. Focusing on this problem, we study instruction tuning LLMs with additional explicit Losses from the Intermediate layer…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2024

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models

Mihir Parmar, Nisarg Patel, Neeraj Varshney, Mutsumi Nakamura, Man Luo, Santosh Mashetty +2
ACL 2024long

Recently developed large language models (LLMs) have been shown to perform remarkably well on a wide range of language understanding tasks. But, can they really “reason” over the natural language? This question has been receiving significant research attention and many reasoning skills such as commo…

Cited by 41Source ↗PDF ↗code ↗Scholar ↗
2024

Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models

Nisarg Patel, Mohith Kulkarni, Mihir Parmar, Aashna Budhiraja, Mutsumi Nakamura, Neeraj Varshney +1
EMNLP 2024main

As Large Language Models (LLMs) continue to exhibit remarkable performance in natural language understanding tasks, there is a crucial need to measure their ability for human-like multi-step logical reasoning. Existing logical reasoning evaluation benchmarks often focus primarily on simplistic singl…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2024

Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter?

Nemika Tyagi, Mihir Parmar, Mohith Kulkarni, Aswin Rrv, Nisarg Patel, Mutsumi Nakamura +2
EMNLP 2024main

Solving grid puzzles involves a significant amount of logical reasoning. Hence, it is a good domain to evaluate reasoning capability of a model which can then guide us to improve the reasoning ability of models. However, most existing works evaluate only the final predicted answer of a puzzle, witho…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

Towards Enhancing Coherence in Extractive Summarization: Dataset and Experiments with LLMs

Mihir Parmar, Hanieh Deilamsalehy, Franck Dernoncourt, Seunghyun Yoon, Ryan A. Rossi, Trung Bui
EMNLP 2024main

Extractive summarization plays a pivotal role in natural language processing due to its wide-range applications in summarizing diverse content efficiently, while also being faithful to the original content. Despite significant advancement achieved in extractive summarization by Large Language Models…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

LogicAttack: Adversarial Attacks for Evaluating Logical Consistency of Natural Language Inference

Mutsumi Nakamura, Santosh Mashetty, Mihir Parmar, Neeraj Varshney, Chitta Baral
EMNLP 2023short findings

Recently Large Language Models (LLMs) such as GPT-3, ChatGPT, and FLAN have led to impressive progress in Natural Language Inference (NLI) tasks. However, these models may rely on simple heuristics or artifacts in the evaluation data to achieve their high performance, which suggests that they still…

Cited by 0Source ↗code ↗Scholar ↗
2022

In-BoXBART: Get Instructions into Biomedical Multi-Task Learning

Mihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, Murad Mohammad, Chitta Baral
NAACL 2022findings

Single-task models have proven pivotal in solving specific tasks; however, they have limitations in real-world applications where multi-tasking is necessary and domain shifts are exhibited. Recently, instructional prompts have shown significant improvement towards multi-task generalization; however,…

Cited by 61Source ↗PDF ↗code ↗Scholar ↗
2022

Less is More: Summary of Long Instructions is Better for Program Synthesis

Kirby Kuznia, Swaroop Mishra, Mihir Parmar, Chitta Baral
EMNLP 2022main

Despite the success of large pre-trained language models (LMs) such as Codex, they show below-par performance on the larger and more complicated programming related questions. We show that LMs benefit from the summarized version of complicated questions. Our findings show that superfluous informatio…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2022

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Atharva Naik +29
EMNLP 2022main

How well can NLP models generalize to a variety of unseen tasks when provided with task instructions? To address this question, we first introduce Super-NaturalInstructions, a benchmark of 1,616 diverse NLP tasks and their expert-written instructions. Our collection covers 76 distinct task types, in…

Cited by 582Source ↗PDF ↗code ↗Scholar ↗