Author name cluster

Somak Aditya

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models

Sayantan Adak
Pratyush Chatterjee
Somnath Banerjee
Rima Hazra
Somak Aditya
Animesh Mukherjee

Present day LLMs face the challenge of managing affordance-based safety risks—situations where outputs inadvertently facilitate harmful actions due to overlooked logical implications. Traditional safety solutions, such as scalar outcome-based reward models, parameter tuning, or heuristic decoding strategies, lack the granularity and proactive nature needed to reliably detect and intervene during subtle yet crucial reasoning steps. Addressing this fundamental gap, we introduce AURA, an innovative, multi-layered framework centered around Process Reward Models (PRMs), providing comprehensive, step level evaluations across logical coherence and safety-awareness. Our framework seamlessly combines introspective self-critique, fine-grained PRM assessments, and adaptive safety-aware decoding to dynamically and proactively guide models toward safer reasoning trajectories. Empirical evidence clearly demonstrates that this approach significantly surpasses existing methods, significantly improving the logical integrity and affordance-sensitive safety of model outputs. This research represents a pivotal step toward safer, more responsible, and contextually aware AI, setting a new benchmark for alignment-sensitive applications.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PRAGWORLD: A Benchmark Evaluating LLMs’ Local World Model Under Minimal Linguistic Alterations and Conversational Dynamics

Sachin Vashistha
Aryan Bibhuti
Atharva Naik
Martin Tutek
Somak Aditya

Real-world conversations are rich with pragmatic elements, such as entity mentions, references, and implicatures. Understanding such nuances is a requirement for successful natural communication, and often requires building a local _world model_ which encodes such elements and captures the dynamics of their evolving states. However, it is not well-understood whether language models (LMs) construct or maintain a robust implicit representation of conversations. In this work, we evaluate the ability of LMs to encode and update their internal world model in dyadic conversations and test their _malleability_ under linguistic alterations. To facilitate this, we apply seven minimal linguistic alterations to conversations sourced from popular conversational QA datasets and construct a benchmark with two variants (i.e., Manual and Synthetic) comprising yes-no questions. We evaluate nine open and one closed source LMs and observe that they struggle to maintain robust accuracy. Our analysis unveils that LMs struggle to memorize crucial details, such as tracking entities under linguistic alterations to conversations. We then propose a dual-perspective interpretability framework which identifies transformer layers that are _useful_ or _harmful_ and highlights linguistic alterations most influenced by harmful layers, typically due to encoding spurious signals or relying on shortcuts. Inspired by these insights, we propose two layer-regularization based fine-tuning strategies that suppress the effect of the harmful layers.

PDF Details DOI

AAAI Conference 2022 System Paper

LITMUS Predictor: An AI Assistant for Building Reliable, High-Performing and Fair Multilingual NLP Systems

Anirudh Srinivasan
Gauri Kholkar
Rahul Kejriwal
Tanuja Ganu
Sandipan Dandapat
Sunayana Sitaram
Balakrishnan Santhanam
Somak Aditya

Pre-trained multilingual language models are gaining popularity due to their cross-lingual zero-shot transfer ability, but these models do not perform equally well in all languages. Evaluating task-specific performance of a model in a large number of languages is often a challenge due to lack of labeled data, as is targeting improvements in low performing languages through few-shot learning. We present a tool - LIT- MUS Predictor - that can make reliable performance projections for a fine-tuned task-specific model in a set of languages without test and training data, and help strategize data labeling efforts to optimize performance and fairness objectives.

PDF Details

AAAI Conference 2020 System Paper

Exploratory Navigation and Selective Reading

Natwar Modani
Paridhi Maheshwari
Harsh Deshpande
Saurab Sirpurkar
Diviya.
Somak Aditya

Navigating a collection of documents can be facilitated by obtaining a human-understandable concept hierarchy with links to the content. This is a non-trivial task for two reasons. First, deﬁning concepts that are understandable by an average consumer and yet meaningful for a large variety of corpora is hard. Second, creating semantically meaningful yet intuitive hierarchical representation is hard, and can be task dependent. We present out system NAVIGATION. AI which automatically processes a document collection, induces a concept hierarchy using Wikipedia and presents an interactive interface that helps user navigate to individual paragraphs using concepts.

PDF Details

IJCAI Conference 2019 Conference Paper

Integrating Knowledge and Reasoning in Image Understanding

Somak Aditya
Yezhou Yang
Chitta Baral

Deep learning based data-driven approaches have been successfully applied in various image understanding applications ranging from object recognition, semantic segmentation to visual question answering. However, the lack of knowledge integration as well as higher-level reasoning capabilities with the methods still pose a hindrance. In this work, we present a brief survey of a few representative reasoning mechanisms, knowledge integration methods and their corresponding image understanding applications developed by various groups of researchers, approaching the problem from a variety of angles. Furthermore, we discuss upon key efforts on integrating external knowledge with neural networks. Taking cues from these efforts, we conclude by discussing potential pathways to improve reasoning capabilities.

PDF Details

UAI Conference 2018 Conference Paper

Combining Knowledge and Reasoning through Probabilistic Soft Logic for Image Puzzle Solving

Somak Aditya
Yezhou Yang
Chitta Baral
Yiannis Aloimonos

The uncertainty associated with human perception is often reduced by one’s extensive prior experience and knowledge. Current datasets and systems do not emphasize the necessity and benefit of using such knowledge. In this work, we propose the task of solving a genre of image-puzzles (“image riddles”) that require both capabilities involving visual detection (including object, activity recognition) and, knowledge-based or commonsense reasoning. Each puzzle involves a set of images and the question “what word connects these images? ”. We compile a dataset of over 3k riddles where each riddle consists of 4 images and a groundtruth answer. The annotations are validated using crowd-sourced evaluation. We also define an automatic evaluation metric to track future progress. Our task bears similarity with the commonly known IQ tasks such as analogy solving, sequence filling that are often used to test intelligence. We develop a Probabilistic Reasoning-based approach that utilizes commonsense knowledge about words and phrases to answer these riddles with a reasonable accuracy. Our approach achieves some promising results for these riddles and provides a strong baseline for future attempts. We make the entire dataset and related materials publicly available to the community (bit. ly/22f9Ala).

Details

AAAI Conference 2018 Conference Paper

Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering

Somak Aditya
Yezhou Yang
Chitta Baral

Many vision and language tasks require commonsense reasoning beyond data-driven image and natural language processing. Here we adopt Visual Question Answering (VQA) as an example task, where a system is expected to answer a question in natural language about an image. Current state-ofthe-art systems attempted to solve the task using deep neural architectures and achieved promising performance. However, the resulting systems are generally opaque and they struggle in understanding questions for which extra knowledge is required. In this paper, we present an explicit reasoning layer on top of a set of penultimate neural network based systems. The reasoning layer enables reasoning and answering questions where additional knowledge is required, and at the same time provides an interpretable interface to the end users. Speciﬁcally, the reasoning layer adopts a Probabilistic Soft Logic (PSL) based engine to reason over a basket of inputs: visual relations, the semantic parse of the question, and background ontological knowledge from word2vec and ConceptNet. Experimental analysis of the answers and the key evidential predicates generated on the VQA dataset validate our approach.

PDF Details

AAAI Conference 2017 Short Paper

Explainable Image Understanding Using Vision and Reasoning

Somak Aditya

Image Understanding is fundamental to intelligent agents.Researchers have explored Caption Generation and VisualQuestion Answering as independent aspects of Image Understanding (Johnson et al. 2015; Xiong, Merity, and Socher2016). Common to most of the successful approaches, are the learning of end-to-end signal mapping (image-to-caption, image and question to answer). The accuracy is impressive. It is also important to explain a decision to end-user(justify the results, and rectify based on feedback). Very recently, there has been some focus (Hendricks et al. 2016;Liu et al. ) on explaining some aspects of the learning systems. In my research, I look towards building explainableImage Understanding systems that can be used to generate captions and answer questions. Humans learn both from examples (learning) and by reading (knowledge). Inspired by such an intuition, researchers have constructed Knowledge-Bases that encode (probabilistic) commonsense and background knowledge. In this work, we look towards efficiently using this probabilistic knowledge on top of machine learning capabilities, to rectify noise in visual detections and generate captions or answers to posed questions.

PDF Details

IJCAI Conference 2015 Conference Paper

Towards Addressing the Winograd Schema Challenge - Building and Using a Semantic Parser and a Knowledge Hunting Module

Arpit Sharma
Nguyen H Vo
Somak Aditya
Chitta Baral

Concerned about the Turing test’s ability to correctly evaluate if a system exhibits human-like intelligence, the Winograd Schema Challenge (WSC) has been proposed as an alternative. A Winograd Schema consists of a sentence and a question. The answers to the questions are intuitive for humans but are designed to be difficult for machines, as they require various forms of commonsense knowledge about the sentence. In this paper we demonstrate our progress towards addressing the WSC. We present an approach that identifies the knowledge needed to answer a challenge question, hunts down that knowledge from text repositories, and then reasons with them to come up with the answer. In the process we develop a semantic parser (www. kparser. org). We show that our approach works well with respect to a subset of Winograd schemas.

PDF Details