Utpal Garain

Akshay Chaturvedi, Swarnadeep Bhar, Soumadeep Saha et al.

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large versions, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions: deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~ 50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.

Soumadeep Saha, Utpal Garain, Arijit Ukil et al.

The enormous demand for annotated data brought forth by deep learning techniques has been accompanied by the problem of annotation noise. Although this issue has been widely discussed in machine learning literature, it has been relatively unexplored in the context of "multi-label classification" (MLC) tasks which feature more complicated kinds of noise. Additionally, when the domain in question has certain logical constraints, noisy annotations often exacerbate their violations, making such a system unacceptable to an expert. This paper studies the effect of label noise on domain rule violation incidents in the MLC task, and incorporates domain rules into our learning algorithm to mitigate the effect of noise. We propose the Domain Obedient Self-supervised Training (DOST) paradigm which not only makes deep learning models more aligned to domain rules, but also improves learning performance in key metrics and minimizes the effect of annotation noise. This novel approach uses domain guidance to detect offending annotations and deter rule-violating predictions in a self-supervised manner, thus making it more "data efficient" and domain compliant. Empirical studies, performed over two large scale multi-label classification datasets, demonstrate that our method results in improvement across the board, and often entirely counteracts the effect of noise.

Soumadeep Saha, Saptarshi Saha, Utpal Garain

Starting with early successes in computer vision tasks, deep learning based techniques have since overtaken state of the art approaches in a multitude of domains. However, it has been demonstrated time and again that these techniques fail to capture semantic context and logical constraints, instead often relying on spurious correlations to arrive at the answer. Since application of deep learning techniques to critical scenarios are dependent on adherence to domain specific constraints, several attempts have been made to address this issue. One limitation holding back a thorough exploration of this area, is a lack of suitable datasets which feature a rich set of rules. In order to address this, we present the VALUE (Vision And Logical Understanding Evaluation) Dataset, consisting of 200,000$+$ annotated images and an associated rule set, based on the popular board game - chess. The curated rule set considerably constrains the set of allowable predictions, and are designed to probe key semantic abilities like localization and enumeration. Alongside standard metrics, additional metrics to measure performance with regards to logical consistency is presented. We analyze several popular and state of the art vision models on this task, and show that, although their performance on standard metrics are laudable, they produce a plethora of incoherent results, indicating that this dataset presents a significant challenge for future works.

Joy Mahapatra, Utpal Garain

Data-to-text (D2T) generation aims to generate human-readable text from semi-structured data, such as tables and graphs. The recent success of D2T is largely attributed to advancements in LLMs. Despite the success of LLMs, no research has been conducted to illustrate the impact of model size on the performance of fine-tuned LLMs for D2T tasks. D2T model performance is typically assessed based on three key qualities: \textit{readability} (indicates fluency and coherence), \textit{informativeness} (measures content similarity), and \textit{faithfulness} (assesses consistency of factual information). It is currently uncertain whether increasing the size of LLMs effectively improves performance in D2T tasks across these three qualities. The objective of this study is to investigate the performance of fine-tuned LLMs in D2T tasks in terms of model size. Through extensive comparative analysis, we aim to elucidate both the advantages and limitations of scaling model sizes across five widely used D2T datasets (E2E, ViGGo, WikiTableText, DART, and WebNLG) and twelve state-of-the-art LLMs with varying sizes from five different LLM families (T5, BART, OPT, BLOOM, and Llama 2). To comprehensively cover all the three essential qualities of D2T models, we incorporate six widely recognized automatic metrics -- \textsc{BLEU}, \textsc{METEOR}, \textsc{BERTScore}, \textsc{MoverScore}, \textsc{Parent}, and \textsc{BARTScore}. We also provide an in-depth analysis of LLM performance concerning model size in the presence of source-reference divergence, a critical aspect of D2T tasks. Our investigation reveals that increasing LLM size enhances \textit{readability} and \textit{informativeness} in D2T tasks, but larger (in terms of size) LLMs may sacrifice \textit{faithfulness}. Moreover, small-sized LLMs show more resilience than larger ones when source-reference divergence is present.

Aditya Shankar Pal, Debojyoti Biswas, Joy Mahapatra et al.

White blood cells (WBCs) play a crucial role in safeguarding the human body against pathogens and foreign substances. Leveraging the abundance of WBC imaging data and the power of deep learning algorithms, automated WBC analysis has the potential for remarkable accuracy. However, the capability of deep learning models to explain their WBC classification remains largely unexplored. In this study, we introduce HemaX, an explainable deep neural network-based model that produces pathologist-like explanations using five attributes: granularity, cytoplasm color, nucleus shape, size relative to red blood cells, and nucleus to cytoplasm ratio (N:C), along with cell classification, localization, and segmentation. HemaX is trained and evaluated on a novel dataset, LeukoX, comprising 467 blood smear images encompassing ten (10) WBC types. The proposed model achieves impressive results, with an average classification accuracy of 81.08% and a Jaccard index of 89.16% for cell localization. Additionally, HemaX performs well in generating the five explanations with a normalized mean square error of 0.0317 for N:C ratio and over 80% accuracy for the other four attributes. Comprehensive experiments comparing against multiple state-of-the-art models demonstrate that HemaX's classification accuracy remains unaffected by its ability to provide explanations. Moreover, empirical analyses and validation by expert hematologists confirm the faithfulness of explanations predicted by our proposed model.

Anabik Pal, Akshay Chaturvedi, Utpal Garain et al.

This paper presents an approach for automatic detection of Munro's Microabscess in stratum corneum (SC) of human skin biopsy in order to realize a machine assisted diagnosis of Psoriasis. The challenge of detecting neutrophils in presence of nucleated cells is solved using the recent advances of deep learning algorithms. Separation of SC layer, extraction of patches from the layer followed by classification of patches with respect to presence or absence of neutrophils form the basis of the overall approach which is effected through an integration of a U-Net based segmentation network and a capsule network for classification. The novel design of the present capsule net leads to a drastic reduction in the number of parameters without any noticeable compromise in the overall performance. The research further addresses the challenge of dealing with Mega-pixel images (in 10X) vis-a-vis Giga-pixel ones (in 40X). The promising result coming out of an experiment on a dataset consisting of 273 real-life images shows that a practical system is possible based on the present research. The implementation of our system is available at https://github.com/Anabik/CapsDeMM.

Saptarshi Saha, Utpal Garain

This paper introduces a simple extension of mixup (Zhang et al., 2018) data augmentation to enhance generalization in visual recognition tasks. Unlike the vanilla mixup method, which blends entire images, our approach focuses on combining regions from multiple images.

Rahul Shah, Soumadeep Saha, Purba Mukherjee et al.

We investigate the prospect of reconstructing the ''cosmic distance ladder'' of the Universe using a novel deep learning framework called LADDER - Learning Algorithm for Deep Distance Estimation and Reconstruction. LADDER is trained on the apparent magnitude data from the Pantheon Type Ia supernovae compilation, incorporating the full covariance information among data points, to produce predictions along with corresponding errors. After employing several validation tests with a number of deep learning models, we pick LADDER as the best performing one. We then demonstrate applications of our method in the cosmological context, including serving as a model-independent tool for consistency checks for other datasets like baryon acoustic oscillations, calibration of high-redshift datasets such as gamma ray bursts, and use as a model-independent mock catalog generator for future probes. Our analysis advocates for careful consideration of machine learning techniques applied to cosmological contexts.

Rahul Shah, Purba Mukherjee, Soumadeep Saha et al.

Conventional calibration of Baryon Acoustic Oscillations (BAO) data relies on estimation of the sound horizon at drag epoch $r_d$ from early universe observations by assuming a cosmological model. We present a recalibration of two independent BAO datasets, SDSS and DESI, by employing deep learning techniques for model-independent estimation of $r_d$, and explore the impacts on $Λ$CDM cosmological parameters. Significant reductions in both Hubble ($H_0$) and clustering ($S_8$) tensions are observed for both the recalibrated datasets. Moderate shifts in some other parameters hint towards further exploration of such data-driven approaches.

Soumadeep Saha, Akshay Chaturvedi, Joy Mahapatra et al.

User authorization-based access privileges are a key feature in many safety-critical systems, but have not been extensively studied in the large language model (LLM) realm. In this work, drawing inspiration from such access control systems, we introduce sudoLLM, a novel framework that results in multi-role aligned LLMs, i.e., LLMs that account for, and behave in accordance with, user access rights. sudoLLM injects subtle user-based biases into queries and trains an LLM to utilize this bias signal in order to produce sensitive information if and only if the user is authorized. We present empirical results demonstrating that this approach shows substantially improved alignment, generalization, resistance to prefix-based jailbreaking attacks, and ``fails-closed''. The persistent tension between the language modeling objective and safety alignment, which is often exploited to jailbreak LLMs, is somewhat resolved with the aid of the injected bias signal. Our framework is meant as an additional security layer, and complements existing guardrail mechanisms for enhanced end-to-end safety with LLMs.

Joy Mahapatra, Utpal Garain

Large Language Models (LLMs) have shown exceptional performance across various Data-to-Text Generation (DTG) tasks. However, generating factually consistent text in DTG remains challenging for LLMs. Despite this, in-depth evaluations of LLM factual consistency for DTG remain missing in the current literature. This paper addresses this gap by providing an extensive evaluation of factual consistency in LLMs for DTG. Our evaluation covers five widely used DTG datasets (E2E, ViGGo, WikiTableText, DART, and WebNLG) and five prominent LLM families (T5, BART, OPT, BLOOM, and Llama 2). To ensure a thorough evaluation of factual consistency, we use four state-of-the-art automatic metrics and include essential human assessments. Our extensive evaluations reveals three key findings regarding factual consistency in LLMs for DTG. First, Llama 2 often excels in generating factually consistent text, although smaller models like T5 and BART can achieve strong factual consistency on larger, lexically less-diverse datasets. Second, the average rate of change (AROC) indicates that increasing model size (number of model trainable parameters) generally enhances factual consistency of LLMs in DTG. Third, we observe that source-reference divergence (i.e., when the reference text diverges semantically from the source) typically reduces the factual consistency of LLMs in DTG.

Saptarshi Saha, Dhruv Vansraj Rathore, Utpal Garain

Most counterfactual inference frameworks traditionally assume acyclic structural causal models (SCMs), i.e. directed acyclic graphs (DAGs). However, many real-world systems (e.g. biological systems) contain feedback loops or cyclic dependencies that violate acyclicity. In this work, we study counterfactual inference in cyclic SCMs under shift-scale interventions, i.e., soft, policy-style changes that rescale and/or shift a variable's mechanism.

Soumadeep Saha, Akshay Chaturvedi, Saptarshi Saha et al.

Chain-of-thought traces have been shown to improve performance of large language models in a plethora of reasoning tasks, yet there is no consensus on the mechanism through which this performance boost is achieved. To shed more light on this, we introduce Causal CoT Graphs (CCGs), which are directed acyclic graphs automatically extracted from reasoning traces that model fine-grained causal dependencies in the language model output. A collection of $1671$ mathematical reasoning problems from MATH500, GSM8K and AIME, and their associated CCGs are compiled into our dataset -- \textbf{KisMATH}. Our detailed empirical analysis with 15 open-weight LLMs shows that (i) reasoning nodes in the CCG are mediators for the final answer, a condition necessary for reasoning; and (ii) LLMs emphasise reasoning paths given by the CCG, indicating that models internally realise structures akin to our graphs. KisMATH enables controlled, graph-aligned interventions and opens up avenues for further investigation into the role of chain-of-thought in LLM reasoning.

Saptarshi Saha, Dhruv Vansraj Rathore, Soumadeep Saha et al.

Quantifying the causal influence of input features within neural networks has become a topic of increasing interest. Existing approaches typically assess direct, indirect, and total causal effects. This work treats NNs as structural causal models (SCMs) and extends our focus to include intrinsic causal contributions (ICC). We propose an identifiable generative post-hoc framework for quantifying ICC. We also draw a relationship between ICC and Sobol' indices. Our experiments on synthetic and real-world datasets demonstrate that ICC generates more intuitive and reliable explanations compared to existing global explanation techniques.

Joy Mahapatra, Soumyajit Roy, Utpal Garain

Monitoring factual inconsistency is essential for ensuring trustworthiness in data-to-text generation (D2T). While large language models (LLMs) have demonstrated exceptional performance across various D2T tasks, previous studies on scaling laws have primarily focused on generalization error through power law scaling to LLM size (i.e., the number of model parameters). However, no research has examined the impact of LLM size on factual inconsistency in D2T. In this paper, we investigate how factual inconsistency in D2T scales with LLM size by exploring two scaling laws: power law and exponential scaling. To rigorously evaluate and compare these scaling laws, we employ a statistical validation framework consisting of three key stages: predictive performance estimation, goodness-of-fit assessment, and comparative analysis. For a comprehensive empirical study, we analyze three popular LLM families across five D2T datasets, measuring factual inconsistency inversely using four state-of-the-art consistency metrics. Our findings, based on exhaustive empirical results and validated through our framework, reveal that, contrary to the widely assumed power law scaling, factual inconsistency in D2T follows an exponential scaling with LLM size.

Soumadeep Saha, Sutanoya Chakraborty, Saptarshi Saha et al.

Crosswords are a form of word puzzle that require a solver to demonstrate a high degree of proficiency in natural language understanding, wordplay, reasoning, and world knowledge, along with adherence to character and length constraints. In this paper we tackle the challenge of solving crosswords with large language models (LLMs). We demonstrate that the current generation of language models shows significant competence at deciphering cryptic crossword clues and outperforms previously reported state-of-the-art (SoTA) results by a factor of 2-3 in relevant benchmarks. We also develop a search algorithm that builds off this performance to tackle the problem of solving full crossword grids with out-of-the-box LLMs for the very first time, achieving an accuracy of 93% on New York Times crossword puzzles. Additionally, we demonstrate that LLMs generalize well and are capable of supporting answers with sound rationale.

Neeraj Kumar Singh, Koyel Ghosh, Joy Mahapatra et al.

Warning: This paper contains examples of the language that some people may find offensive. Detecting and reducing hateful, abusive, offensive comments is a critical and challenging task on social media. Moreover, few studies aim to mitigate the intensity of hate speech. While studies have shown that context-level semantics are crucial for detecting hateful comments, most of this research focuses on English due to the ample datasets available. In contrast, low-resource languages, like Indian languages, remain under-researched because of limited datasets. Contrary to hate speech detection, hate intensity reduction remains unexplored in high-resource and low-resource languages. In this paper, we propose a novel end-to-end model, HCDIR, for Hate Context Detection, and Hate Intensity Reduction in social media posts. First, we fine-tuned several pre-trained language models to detect hateful comments to ascertain the best-performing hateful comments detection model. Then, we identified the contextual hateful words. Identification of such hateful words is justified through the state-of-the-art explainable learning model, i.e., Integrated Gradient (IG). Lastly, the Masked Language Modeling (MLM) model has been employed to capture domain-specific nuances to reduce hate intensity. We masked the 50\% hateful words of the comments identified as hateful and predicted the alternative words for these masked terms to generate convincing sentences. An optimal replacement for the original hate comments from the feasible sentences is preferred. Extensive experiments have been conducted on several recent datasets using automatic metric-based evaluation (BERTScore) and thorough human evaluation. To enhance the faithfulness in human evaluation, we arranged a group of three human annotators with varied expertise.

Omid Mohamad Nezami, Akshay Chaturvedi, Mark Dras et al.

Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we present the first type-specific approach to generating adversarial examples for object detection, which entails detecting bounding boxes around multiple objects present in the image and classifying them at the same time, making it a harder task than against image classification. We specifically aim to attack the widely used Faster R-CNN by changing the predicted label for a particular object in an image: where prior work has targeted one specific object (a stop sign), we generalise to arbitrary objects, with the key challenge being the need to change the labels of all bounding boxes for all instances of that object type. To do so, we propose a novel method, named Pick-Object-Attack. Pick-Object-Attack successfully adds perturbations only to bounding boxes for the targeted object, preserving the labels of other detected objects in the image. In terms of perceptibility, the perturbations induced by the method are very small. Furthermore, for the first time, we examine the effect of adversarial attacks on object detection in terms of a downstream task, image captioning; we show that where a method that can modify all object types leads to very obvious changes in captions, the changes from our constrained attack are much less apparent.

Akshay Chaturvedi, Abijith KP, Utpal Garain

Neural machine translation (NMT) systems have been shown to give undesirable translation when a small change is made in the source sentence. In this paper, we study the behaviour of NMT systems when multiple changes are made to the source sentence. In particular, we ask the following question "Is it possible for an NMT system to predict same translation even when multiple words in the source sentence have been replaced?". To this end, we propose a soft-attention based technique to make the aforementioned word replacements. The experiments are conducted on two language pairs: English-German (en-de) and English-French (en-fr) and two state-of-the-art NMT systems: BLSTM-based encoder-decoder with attention and Transformer. The proposed soft-attention based technique achieves high success rate and outperforms existing methods like HotFlip by a significant margin for all the conducted experiments. The results demonstrate that state-of-the-art NMT systems are unable to capture the semantics of the source language. The proposed soft-attention based technique is an invariance-based adversarial attack on NMT systems. To better evaluate such attacks, we propose an alternate metric and argue its benefits in comparison with success rate.

Akshay Chaturvedi, Utpal Garain

At present, adversarial attacks are designed in a task-specific fashion. However, for downstream computer vision tasks such as image captioning, image segmentation etc., the current deep learning systems use an image classifier like VGG16, ResNet50, Inception-v3 etc. as a feature extractor. Keeping this in mind, we propose Mimic and Fool, a task agnostic adversarial attack. Given a feature extractor, the proposed attack finds an adversarial image which can mimic the image feature of the original image. This ensures that the two images give the same (or similar) output regardless of the task. We randomly select 1000 MSCOCO validation images for experimentation. We perform experiments on two image captioning models, Show and Tell, Show Attend and Tell and one VQA model, namely, end-to-end neural module network (N2NMN). The proposed attack achieves success rate of 74.0%, 81.0% and 87.1% for Show and Tell, Show Attend and Tell and N2NMN respectively. We also propose a slight modification to our attack to generate natural-looking adversarial images. In addition, we also show the applicability of the proposed attack for invertible architecture. Since Mimic and Fool only requires information about the feature extractor of the model, it can be considered as a gray-box attack.

Anabik Pal, Sounak Ray, Utpal Garain

In this paper, a deep neural network based ensemble method is experimented for automatic identification of skin disease from dermoscopic images. The developed algorithm is applied on the task3 of the ISIC 2018 challenge dataset (Skin Lesion Analysis Towards Melanoma Detection).

Snehasis Banerjee, Tanushyam Chattopadhyay, Arpan Pal et al.

This paper presents an approach for automation of interpretable feature selection for Internet Of Things Analytics (IoTA) using machine learning (ML) techniques. Authors have conducted a survey over different people involved in different IoTA based application development tasks. The survey reveals that feature selection is the most time consuming and niche skill demanding part of the entire workflow. This paper shows how feature selection is successfully automated without sacrificing the decision making accuracy and thereby reducing the project completion time and cost of hiring expensive resources. Several pattern recognition principles and state of art (SoA) ML techniques are followed to design the overall approach for the proposed automation. Three data sets are considered to establish the proof-of-concept. Experimental results show that the proposed automation is able to reduce the time for feature selection to $2$ days instead of $4-6$ months which would have been required in absence of the automation. This reduction in time is achieved without any sacrifice in the accuracy of the decision making process. Proposed method is also compared against Multi Layer Perceptron (MLP) model as most of the state of the art works on IoTA uses MLP based Deep Learning. Moreover the feature selection method is compared against SoA feature reduction technique namely Principal Component Analysis (PCA) and its variants. The results obtained show that the proposed method is effective.

Snehasis Banerjee, Tanushyam Chattopadhyay, Swagata Biswas et al.

In this paper, a Wide Learning architecture is proposed that attempts to automate the feature engineering portion of the machine learning (ML) pipeline. Feature engineering is widely considered as the most time consuming and expert knowledge demanding portion of any ML task. The proposed feature recommendation approach is tested on 3 healthcare datasets: a) PhysioNet Challenge 2016 dataset of phonocardiogram (PCG) signals, b) MIMIC II blood pressure classification dataset of photoplethysmogram (PPG) signals and c) an emotion classification dataset of PPG signals. While the proposed method beats the state of the art techniques for 2nd and 3rd dataset, it reaches 94.38% of the accuracy level of the winner of PhysioNet Challenge 2016. In all cases, the effort to reach a satisfactory performance was drastically less (a few days) than manual feature engineering.

Dwaipayan Roy, Debjyoti Paul, Mandar Mitra et al.

In this paper a framework for Automatic Query Expansion (AQE) is proposed using distributed neural language model word2vec. Using semantic and contextual relation in a distributed and unsupervised framework, word2vec learns a low dimensional embedding for each vocabulary entry. Using such a framework, we devise a query expansion technique, where related terms to a query are obtained by K-nearest neighbor approach. We explore the performance of the AQE methods, with and without feedback query expansion, and a variant of simple K-nearest neighbor in the proposed framework. Experiments on standard TREC ad-hoc data (Disk 4, 5 with query sets 301-450, 601-700) and web data (WT10G data with query set 451-550) shows significant improvement over standard term-overlapping based retrieval methods. However the proposed method fails to achieve comparable performance with statistical co-occurrence based feedback method such as RM3. We have also found that the word2vec based query expansion methods perform similarly with and without any feedback information.

Arjun Das, Utpal Garain

This paper describes performance of CRF based systems for Named Entity Recognition (NER) in Indian language as a part of ICON 2013 shared task. In this task we have considered a set of language independent features for all the languages. Only for English a language specific feature, i.e. capitalization, has been added. Next the use of gazetteer is explored for Bengali, Hindi and English. The gazetteers are built from Wikipedia and other sources. Test results show that the system achieves the highest F measure of 88% for English and the lowest F measure of 69% for both Tamil and Telugu. Note that for the least performing two languages no gazetteer was used. NER in Bengali and Hindi finds accuracy (F measure) of 87% and 79%, respectively.

Ankush Roy, Biswajit Halder, Utpal Garain et al.

Automatic authentication of paper money has been targeted. Indian bank notes are taken as reference to show how a system can be developed for discriminating fake notes from genuine ones. Image processing and pattern recognition techniques are used to design the overall approach. The ability of the embedded security aspects is thoroughly analysed for detecting fake currencies. Real forensic samples are involved in the experiment that shows a high precision machine can be developed for authentication of paper money. The system performance is reported in terms of both accuracy and processing speed. Comparison with human subjects namely forensic experts and bank staffs clearly shows its applicability for mass checking of currency notes in the real world. The analysis of security features to protect counterfeiting highlights some facts that should be taken care of in future designing of currency notes.