AIConfPaper
← Search

Shashank Srivastava

27 accepted papers

2026

DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing

Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep P. Chinchali +1
ICLR 2026poster

Current image immunization defense techniques against diffusion-based editing embed imperceptible noise into target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming optimization for each image separately, taking hours for small batc…

Cited by 0Source ↗code ↗Scholar ↗
2026

Directly Optimizing Natural Language Explanations for Behavioral Faithfulness: Simulatability and Recoverability

Advaith Malladi, Shashank Srivastava
ICML 2026poster

Natural-language explanations are widely used to interpret machine learning models, yet many prioritize human plausibility over accurately reflecting or predicting model behavior. Prior approaches often rely on human-written rationales, producing post-hoc explanations that neither align with the mod…

Cited by 0Source ↗Scholar ↗
2025

Classifying Unreliable Narrators with Large Language Models

Anneliese Brei, Katharine Henry, Abhisheik Sharma, Shashank Srivastava, Snigdha Chaturvedi
ACL 2025long

Often when we interact with a first-person account of events, we consider whether or not the narrator, the primary speaker of the text, is reliable. In this paper, we propose using computational methods to identify unreliable narrators, i.e. those who unintentionally misrepresent information. Borrow…

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

Explaining Differences Between Model Pairs in Natural Language through Sample Learning

Advaith Malladi, Rakesh R Menon, Yuvraj Jain, Shashank Srivastava
EMNLP 2025

With the growing adoption of machine learning models in critical domains, techniques for explaining differences between models have become essential for trust, debugging, and informed deployment. Previous approaches address this by identifying input transformations that cause divergent predictions o

Cited by 0Source ↗PDF ↗Scholar ↗
2025

INTERACT: Enabling Interactive, Question-Driven Learning in Large Language Models

Aum Kendapadi, Kerem Zaman, Rakesh R Menon, Shashank Srivastava
ACL 2025long

Large language models (LLMs) excel at answering questions but remain passive learners—absorbing static data without the ability to question and refine knowledge. This paper explores how LLMs can transition to interactive, question-driven learning through student-teacher dialogues. We introduce INTER…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers

Rakesh R Menon, Shashank Srivastava
EMNLP 2024main

Despite their high predictive accuracies, current machine learning systems often exhibit systematic biases stemming from annotation artifacts or insufficient support for certain classes in the dataset. Recent work proposes automatic methods for identifying and explaining systematic biases using keyw…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion

Kerem Zaman, Leshem Choshen, Shashank Srivastava
EMNLP 2024main

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce unwanted knowledge. We investigate the effects of model fusion i…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2024

Online Reinforcement Learning-Based Pedagogical Planning for Narrative-Centered Learning Environments

Fahmid Morshed Fahid, Jonathan Rowe, Yeojin Kim, Shashank Srivastava, James Lester
AAAI 2024technical

Pedagogical planners can provide adaptive support to students in narrative-centered learning environments by dynamically scaffolding student learning and tailoring problem scenarios. Reinforcement learning (RL) is frequently used for pedagogical planning in narrative-centered learning environments.…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

SocialGaze: Improving the Integration of Human Social Norms in Large Language Models

Anvesh Rao Vijjini, Rakesh R Menon, Jiayi Fu, Shashank Srivastava, Snigdha Chaturvedi
EMNLP 2024finding

While much research has explored enhancing the reasoning capabilities of large language models (LLMs) in the last few years, there is a gap in understanding the alignment of these models with social values and norms. We introduce the task of judging social acceptance. Social acceptance requires mode…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture

Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis, Sayan Ghosh, Lihong He +5
EMNLP 2023long findings

Real-world domain experts (e.g., doctors) rarely annotate only a decision label in their day-to-day workflow without providing explanations. Yet, existing low-resource learning techniques, such as Active Learning (AL), that aim to support human annotators mostly focus on the label while neglecting t…

Cited by 0Source ↗code ↗Scholar ↗
2023

LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning

Sayan Ghosh, Rakesh R. Menon, Shashank Srivastava
ACL 2023findings

A hallmark of human intelligence is the ability to learn new concepts purely from language. Several recent approaches have explored training machine learning models via natural language supervision. However, these approaches fall short in leveraging linguistic quantifiers (such as ‘always’ or ‘rarel…

Cited by 2Source ↗PDF ↗Scholar ↗
2023

Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers

Kangda Wei, Sayan Ghosh, Rakesh R Menon, Shashank Srivastava
EMNLP 2023long findings

Recent approaches have explored language- guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022). While these classifiers can generalize in zero-shot settin…

Cited by 0Source ↗code ↗Scholar ↗
2023

Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models

Yiyuan Li, Rakesh R Menon, Sayan Ghosh, Shashank Srivastava
EMNLP 2023long main

Generalized quantifiers (e.g., $\textit{few}$, $\textit{most}$) are used to indicate the proportions predicates satisfy (for example, $\textit{some}$ apples are red). One way to interpret quantifier semantics is to explicitly bind these satisfactions with percentage scopes (e.g., 30%-40% of apples a…

Cited by 0Source ↗code ↗Scholar ↗
2022

CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations

Rakesh R. Menon, Sayan Ghosh, Shashank Srivastava
ACL 2022long

Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, a hallmark of human intelligence is the ability to learn new concepts purely from language. Here, we explore training zero-shot classifiers for structured data purely from langua…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding

Sayan Ghosh, Shashank Srivastava
ACL 2022long

While large language models have shown exciting progress on several NLP benchmarks, evaluating their ability for complex analogical reasoning remains under-explored. Here, we introduce a high-quality crowdsourced dataset of narratives for employing proverbs in context as a benchmark for abstract lan…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2021

Adversarial Scrubbing of Demographic Information for Text Classification

Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier Oliva, Shashank Srivastava, Snigdha Chaturvedi
EMNLP 2021main

Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair representations while maintaining performance on the…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2021

How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation?

Sayan Ghosh, Zheng Qi, Snigdha Chaturvedi, Shashank Srivastava
ACL 2021short

Existing approaches for the Table-to-Text task suffer from issues such as missing information, hallucination and repetition. Many approaches to this problem use Reinforcement Learning (RL), which maximizes a single manually defined reward, such as BLEU. In this work, we instead pose the Table-to-Tex…

Cited by 15Source ↗PDF ↗code ↗Scholar ↗
2021

Improving and Simplifying Pattern Exploiting Training

Derek Tam, Rakesh R. Menon, Mohit Bansal, Shashank Srivastava, Colin Raffel
EMNLP 2021main

Recently, pre-trained language models (LMs) have achieved strong performance when fine-tuned on difficult benchmarks like SuperGLUE. However, performance can suffer when there are very few labeled examples available for fine-tuning. Pattern Exploiting Training (PET) is a recent approach that leverag…

Cited by 156Source ↗PDF ↗code ↗Scholar ↗
2021

Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning

Sayan Ghosh, Shashank Srivastava
EMNLP 2021finding

Mapping natural language instructions to programs that computers can process is a fundamental challenge. Existing approaches focus on likelihood-based training or using reinforcement learning to fine-tune models based on a single reward. In this paper, we pose program generation from language as Inv…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗