Jaspreet Singh

Jaspreet Singh, Chandan Singh · berkeley

The convolutional layers of standard convolutional neural networks (CNNs) are equivariant to translation. However, the convolution and fully-connected layers are not equivariant or invariant to other affine geometric transformations. Recently, a new class of CNNs is proposed in which the conventional layers of CNNs are replaced with equivariant convolution, pooling, and batch-normalization layers. The final classification layer in equivariant neural networks is invariant to different affine geometric transformations such as rotation, reflection and translation, and the scalar value is obtained by either eliminating the spatial dimensions of filter responses using convolution and down-sampling throughout the network or average is taken over the filter responses. In this work, we propose to integrate the orthogonal moments which gives the high-order statistics of the function as an effective means for encoding global invariance with respect to rotation, reflection and translation in fully-connected layers. As a result, the intermediate layers of the network become equivariant while the classification layer becomes invariant. The most widely used Zernike, pseudo-Zernike and orthogonal Fourier-Mellin moments are considered for this purpose. The effectiveness of the proposed work is evaluated by integrating the invariant transition and fully-connected layer in the architecture of group-equivariant CNNs (G-CNNs) on rotated MNIST and CIFAR10 datasets.

Jaspreet Singh, Petra Bosilj, Grzegorz Cielniak

The convolutional neural networks (CNNs) are not inherently shift invariant or equivariant. The downsampling operation, used in CNNs, is one of the key reasons which breaks the shift invariant property of a CNN. Conversely, downsampling operation is important to improve computational efficiency and increase the area of the receptive field for more contextual information. In this work, we propose Gaussian-Hermite Sampling (GHS), a novel downsampling strategy designed to achieve accurate shift invariance. GHS leverages Gaussian-Hermite polynomials to perform shift-consistent sampling, enabling CNN layers to maintain invariance to arbitrary spatial shifts prior to training. When integrated into standard CNN architectures, the proposed method embeds shift invariance directly at the layer level without requiring architectural modifications or additional training procedures. We evaluate the proposed approach on CIFAR-10, CIFAR-100, and MNIST-rot datasets. Experimental results demonstrate that GHS significantly improves shift consistency, achieving 100% classification consistency under spatial shifts, while also improving classification accuracy compared to baseline CNN models.

Gunbir Singh Baveja, Jaspreet Singh

Earthquake prediction has been a challenging research area for many decades, where the future occurrence of this highly uncertain calamity is predicted. In this paper, several parametric and non-parametric features were calculated, where the non-parametric features were calculated using the parametric features. $8$ seismic features were calculated using Gutenberg-Richter law, the total recurrence, and the seismic energy release. Additionally, criterions such as Maximum Relevance and Maximum Redundancy were applied to choose the pertinent features. These features along with others were used as input for an Extreme Learning Machine (ELM) Regression Model. Magnitude and time data of $5$ decades from the Assam-Guwahati region were used to create this model for magnitude prediction. The Testing Accuracy and Testing Speed were computed taking the Root Mean Squared Error (RMSE) as the parameter for evaluating the mode. As confirmed by the results, ELM shows better scalability with much faster training and testing speed (up to a thousand times faster) than traditional Support Vector Machines. The testing RMSE came out to be around $0.097$. To further test the model's robustness -- magnitude-time data from California was used to calculate the seismic indicators which were then fed into an ELM and then tested on the Assam-Guwahati region. The model proves to be robust and can be implemented in early warning systems as it continues to be a major part of Disaster Response and management.

Harpreet Singh, Jaspreet Singh, Satwant Singh et al.

The rapid proliferation of Generative Artificial Intelligence (GenAI) is reshaping pedagogical practices and assessment models in higher education. While institutional and educator perspectives on GenAI integration are increasingly documented, the student perspective remains comparatively underexplored. This study examines how students perceive, use, and evaluate GenAI within their academic practices, focusing on usage patterns, perceived benefits, and expectations for institutional support. Data were collected through a questionnaire administered to 436 postgraduate Computer Science students at the University of Hertfordshire and analysed using descriptive methods. The findings reveal a Confidence-Competence Paradox: although more than 60% of students report high familiarity with tools such as ChatGPT, daily academic use remains limited and confidence in effective application is only moderate. Students primarily employ GenAI for cognitive scaffolding tasks, including concept clarification and brainstorming, rather than fully automated content generation. At the same time, respondents express concerns regarding data privacy, reliability of AI-generated information, and the potential erosion of critical thinking skills. The results also indicate strong student support for integrating AI literacy into curricula and programme Knowledge, Skills, and Behaviours (KSBs). Overall, the study suggests that universities should move beyond a policing approach to GenAI and adopt a pedagogical framework that emphasises AI literacy, ethical guidance, and equitable access to AI tools.

Liza Darwesh, Jaspreet Singh, Marin Marian et al.

This study investigates the elicitation of empathy toward a third party through interaction with social agents. Participants engaged with either a physical robot or a voice-enabled chatbot, both driven by a large language model (LLM) programmed to exhibit either an empathetic tone or remain neutral. The interaction is focused on a fictional character, Katie Banks, who is in a challenging situation and in need of financial donations. The willingness to help Katie, measured by the number of hours participants were willing to volunteer, along with their perceptions of the agent, were assessed for 60 participants. Results indicate that neither robotic embodiment nor empathetic tone significantly influenced participants' willingness to volunteer. While the LLM effectively simulated human empathy, fostering genuine empathetic responses in participants proved challenging.

Michael Völske, Alexander Bondarenko, Maik Fröbe et al.

Recently, neural networks have been successfully employed to improve upon state-of-the-art performance in ad-hoc retrieval tasks via machine-learned ranking functions. While neural retrieval models grow in complexity and impact, little is understood about their correspondence with well-studied IR principles. Recent work on interpretability in machine learning has provided tools and techniques to understand neural models in general, yet there has been little progress towards explaining ranking models. We investigate whether one can explain the behavior of neural ranking models in terms of their congruence with well understood principles of document ranking by using established theories from axiomatic IR. Axiomatic analysis of information retrieval models has formalized a set of constraints on ranking decisions that reasonable retrieval models should fulfill. We operationalize this axiomatic thinking to reproduce rankings based on combinations of elementary constraints. This allows us to investigate to what extent the ranking decisions of neural rankers can be explained in terms of retrieval axioms, and which axioms apply in which situations. Our experimental study considers a comprehensive set of axioms over several representative neural rankers. While the existing axioms can already explain the particularly confident ranking decisions rather well, future work should extend the axiom set to also cover the other still "unexplainable" neural IR rank decisions.

Jonas Wallat, Jaspreet Singh, Avishek Anand

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this article, we probe BERT specifically to understand and measure the relational knowledge it captures in its parametric memory. While probing for linguistic understanding is commonly applied to all layers of BERT as well as fine-tuned models, this has not been done for factual knowledge. We utilize existing knowledge base completion tasks (LAMA) to probe every layer of pre-trained as well as fine-tuned BERT models(ranking, question answering, NER). Our findings show that knowledge is not just contained in BERT's final layers. Intermediate layers contribute a significant amount (17-60%) to the total knowledge found. Probing intermediate layers also reveals how different types of knowledge emerge at varying rates. When BERT is fine-tuned, relational knowledge is forgotten. The extent of forgetting is impacted by the fine-tuning objective and the training data. We found that ranking models forget the least and retain more knowledge in their final layer compared to masked language modeling and question-answering. However, masked language modeling performed the best at acquiring new knowledge from the training data. When it comes to learning facts, we found that capacity and fact density are key factors. We hope this initial work will spur further research into understanding the parametric memory of language models and the effect of training objectives on factual knowledge. The code to repeat the experiments is publicly available on GitHub.

Zijian Zhang, Jaspreet Singh, Ujwal Gadiraju et al.

Complex machine learning models are deployed in several critical domains including healthcare and autonomous vehicles nowadays, albeit as functional black boxes. Consequently, there has been a recent surge in interpreting decisions of such complex models in order to explain their actions to humans. Models that correspond to human interpretation of a task are more desirable in certain contexts and can help attribute liability, build trust, expose biases and in turn build better models. It is, therefore, crucial to understand how and which models conform to human understanding of tasks. In this paper, we present a large-scale crowdsourcing study that reveals and quantifies the dissonance between human and machine understanding, through the lens of an image classification task. In particular, we seek to answer the following questions: Which (well-performing) complex ML models are closer to humans in their use of features to make accurate predictions? How does task difficulty affect the feature selection capability of machines in comparison to humans? Are humans consistently better at selecting features that make image recognition more accurate? Our findings have important implications on human-machine collaboration, considering that a long term goal in the field of artificial intelligence is to make machines capable of learning and reasoning like humans.

Jonas Wallat, Jaspreet Singh, Avishek Anand

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this paper, we probe BERT specifically to understand and measure the relational knowledge it captures. We utilize knowledge base completion tasks to probe every layer of pre-trained as well as fine-tuned BERT (ranking, question answering, NER). Our findings show that knowledge is not just contained in BERT's final layers. Intermediate layers contribute a significant amount (17-60%) to the total knowledge found. Probing intermediate layers also reveals how different types of knowledge emerge at varying rates. When BERT is fine-tuned, relational knowledge is forgotten but the extent of forgetting is impacted by the fine-tuning objective but not the size of the dataset. We found that ranking models forget the least and retain more knowledge in their final layer. We release our code on github to repeat the experiments.

Jaspreet Singh, Zhenye Wang, Megha Khosla et al.

Learning-to-rank (LTR) is a class of supervised learning techniques that apply to ranking problems dealing with a large number of features. The popularity and widespread application of LTR models in prioritizing information in a variety of domains makes their scrutability vital in today's landscape of fair and transparent learning systems. However, limited work exists that deals with interpreting the decisions of learning systems that output rankings. In this paper we propose a model agnostic local explanation method that seeks to identify a small subset of input features as explanation to a ranking decision. We introduce new notions of validity and completeness of explanations specifically for rankings, based on the presence or absence of selected features, as a way of measuring goodness. We devise a novel optimization problem to maximize validity directly and propose greedy algorithms as solutions. In extensive quantitative experiments we show that our approach outperforms other model agnostic explanation approaches across pointwise, pairwise and listwise LTR models in validity while not compromising on completeness.

Gaurav Kumar, Rishabh Joshi, Jaspreet Singh et al.

The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are crucial for generating responses in a chit-chat system. To overcome this problem, we propose an end to end multi-stream deep learning architecture which learns unified embeddings for query-response pairs by leveraging contextual information from memory networks and syntactic information by incorporating Graph Convolution Networks (GCN) over their dependency parse. A stream of this network also utilizes transfer learning by pre-training a bidirectional transformer to extract semantic representation for each input sentence and incorporates external knowledge through the the neighborhood of the entities from a Knowledge Base (KB). We benchmark these embeddings on next sentence prediction task and significantly improve upon the existing techniques. Furthermore, we use AMUSED to represent query and responses along with its context to develop a retrieval based conversational agent which has been validated by expert linguists to have comprehensive engagement with humans.

Abdul Karim, Jaspreet Singh, Avinash Mishra et al.

Prediction of toxicity levels of chemical compounds is an important issue in Quantitative Structure-Activity Relationship (QSAR) modeling. Although toxicity prediction has achieved significant progress in recent times through deep learning, prediction accuracy levels obtained by even very recent methods are not yet very high. We propose a multimodal deep learning method using multiple heterogeneous neural network types and data representations. We represent chemical compounds by strings, images, and numerical features. We train fully connected, convolutional, and recurrent neural networks and their ensembles. Each data representation or neural network type has its own strengths and weaknesses. Our motivation is to obtain a collective performance that could go beyond individual performance of each data representation or each neural network type. On a standard toxicity benchmark, our proposed method obtains significantly better accuracy levels than that by the state-of-the-art toxicity prediction methods.

Zeon Trevor Fernando, Jaspreet Singh, Avishek Anand

A recent trend in IR has been the usage of neural networks to learn retrieval models for text based adhoc search. While various approaches and architectures have yielded significantly better performance than traditional retrieval models such as BM25, it is still difficult to understand exactly why a document is relevant to a query. In the ML community several approaches for explaining decisions made by deep neural networks have been proposed -- including DeepSHAP which modifies the DeepLift algorithm to estimate the relative importance (shapley values) of input features for a given decision by comparing the activations in the network for a given image against the activations caused by a reference input. In image classification, the reference input tends to be a plain black image. While DeepSHAP has been well studied for image classification tasks, it remains to be seen how we can adapt it to explain the output of Neural Retrieval Models (NRMs). In particular, what is a good "black" image in the context of IR? In this paper we explored various reference input document construction techniques. Additionally, we compared the explanations generated by DeepSHAP to LIME (a model agnostic approach) and found that the explanations differ considerably. Our study raises concerns regarding the robustness and accuracy of explanations produced for NRMs. With this paper we aim to shed light on interesting problems surrounding interpretability in NRMs and highlight areas of future work.

Avishek Anand, Megha Khosla, Jaspreet Singh et al.

Word embeddings are a powerful approach for analyzing language and have been widely popular in numerous tasks in information retrieval and text mining. Training embeddings over huge corpora is computationally expensive because the input is typically sequentially processed and parameters are synchronously updated. Distributed architectures for asynchronous training that have been proposed either focus on scaling vocabulary sizes and dimensionality or suffer from expensive synchronization latencies. In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings. Our training procedure does not involve any parameter synchronization except a final sub-model merge phase that typically executes in a few minutes. Our distributed training scales seamlessly to large corpus sizes and we get comparable and sometimes even up to 45% performance improvement in a variety of NLP benchmarks using models trained by our distributed procedure which requires $1/10$ of the time taken by the baseline approach. Finally we also show that we are robust to missing words in sub-models and are able to effectively reconstruct word representations.

Jaspreet Singh, Wolfgang Nejdl, Avishek Anand

Archives are an important source of study for various scholars. Digitization and the web have made archives more accessible and led to the development of several time-aware exploratory search systems. However these systems have been designed for more general users rather than scholars. Scholars have more complex information needs in comparison to general users. They also require support for corpus creation during their exploration process. In this paper we present Expedition - a time-aware exploratory search system that addresses the requirements and information needs of scholars. Expedition possesses a suite of ad-hoc and diversity based retrieval models to address complex information needs; a newspaper-style user interface to allow for larger textual previews and comparisons; entity filters to more naturally refine a result list and an interactive annotated timeline which can be used to better identify periods of importance.

Jaspreet Singh, Avishek Anand

Longitudinal corpora like legal, corporate and newspaper archives are of immense value to a variety of users, and time as an important factor strongly influences their search behavior in these archives. While many systems have been developed to support users temporal information needs, questions remain over how users utilize these advances to satisfy their needs. Analyzing their search behavior will provide us with novel insights into search strategy, guide better interface and system design and highlight new problems for further research. In this paper we propose a set of search tasks, with varying complexity, that IIR researchers can utilize to study user search behavior in archives. We discuss how we created and refined these tasks as the result of a pilot study using a temporal search engine. We not only propose task descriptions but also pre and post-task evaluation mechanisms that can be employed for a large-scale study (crowdsourcing). Our initial findings show the viability of such tasks for investigating search behavior in archives.

Jaspreet Singh, Johannes Hoffart, Avishek Anand

Linking entities like people, organizations, books, music groups and their songs in text to knowledge bases (KBs) is a fundamental task for many downstream search and mining applications. Achieving high disambiguation accuracy crucially depends on a rich and holistic representation of the entities in the KB. For popular entities, such a representation can be easily mined from Wikipedia, and many current entity disambiguation and linking methods make use of this fact. However, Wikipedia does not contain long-tail entities that only few people are interested in, and also at times lags behind until newly emerging entities are added. For such entities, mining a suitable representation in a fully automated fashion is very difficult, resulting in poor linking accuracy. What can automatically be mined, though, is a high-quality representation given the context of a new entity occurring in any text. Due to the lack of knowledge about the entity, no method can retrieve these occurrences automatically with high precision, resulting in a chicken-egg problem. To address this, our approach automatically generates candidate occurrences of entities, prompting the user for feedback to decide if the occurrence refers to the actual entity in question. This feedback gradually improves the knowledge and allows our methods to provide better candidate suggestions to keep the user engaged. We propose novel human-in-the-loop retrieval methods for generating candidates based on gradient interleaving of diversification and textual relevance approaches. We conducted extensive experiments on the FACC dataset, showing that our approaches convincingly outperform carefully selected baselines in both intrinsic and extrinsic measures while keeping users engaged.

Jaspreet Singh, Wolfgang Nejdl, Avishek Anand

Longitudinal corpora like newspaper archives are of immense value to historical research, and time as an important factor for historians strongly influences their search behaviour in these archives. While searching for articles published over time, a key preference is to retrieve documents which cover the important aspects from important points in time which is different from standard search behavior. To support this search strategy, we introduce the notion of a Historical Query Intent to explicitly model a historian's search task and define an aspect-time diversification problem over news archives. We present a novel algorithm, HistDiv, that explicitly models the aspects and important time windows based on a historian's information seeking behavior. By incorporating temporal priors based on publication times and temporal expressions, we diversify both on the aspect and temporal dimensions. We test our methods by constructing a test collection based on The New York Times Collection with a workload of 30 queries of historical intent assessed manually. We find that HistDiv outperforms all competitors in subtopic recall with a slight loss in precision. We also present results of a qualitative user study to determine wether this drop in precision is detrimental to user experience. Our results show that users still preferred HistDiv's ranking.

Jaspreet Singh, Avishek Anand

Given the recent interest in arguably accurate yet non-interpretable neural models, even with textual features, for document ranking we try to answer questions relating to how to interpret rankings. In this paper we take first steps towards a framework for the interpretability of retrieval models with the aim of answering 3 main questions "What is the intent of the query according to the ranker?", "Why is a document ranked higher than another for the query?" and "Why is a document relevant to the query?" Our framework is predicated on the assumption that text based retrieval model behavior can be estimated using query expansions in conjunction with a simpler retrieval model irrespective of the underlying ranker. We conducted experiments with the Clueweb test collection. We show how our approach performs for both simpler models with a closed form notation (which allows us to measure the accuracy of the interpretation) and neural ranking models. Our results indicate that we can indeed interpret more complex models with reasonable accuracy under certain simplifying assumptions. In a case study we also show our framework can be employed to interpret the results of the DRMM neural retrieval model in various scenarios.

Jaspreet Singh, Avishek Anand

Retrieval models in information retrieval are used to rank documents for typically under-specified queries. Today machine learning is used to learn retrieval models from click logs and/or relevance judgments that maximizes an objective correlated with user satisfaction. As these models become increasingly powerful and sophisticated, they also become harder to understand. Consequently, it is hard for to identify artifacts in training, data specific biases and intents from a complex trained model like neural rankers even if trained purely on text features. EXS is a search system designed specifically to provide its users with insight into the following questions: `What is the intent of the query according to the ranker?', `Why is this document ranked higher than another?' and `Why is this document relevant to the query?'. EXS uses a version of a popular posthoc explanation method for classifiers -- LIME, adapted specifically to answer these questions. We show how such a system can effectively help a user understand the results of neural rankers and highlight areas of improvement.

Jaspreet Singh, Avishek Anand

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features influence the model prediction avoiding algorithmic transparency. Rankings are ordering over items encoding implicit comparisons typically learned using a family of features using learning-to-rank models. In this paper we focus on how best we can understand the decisions made by a ranker in a post-hoc model agnostic manner. We operate on the notion of interpretability based on explainability of rankings over an interpretable feature space. Furthermore we train a tree based model (inherently interpretable) using labels from the ranker, called secondary training data to provide explanations. Consequently, we attempt to study how well does a subset of features, potentially interpretable, explain the full model under different training sizes and algorithms. We do experiments on the learning to rank datasets with 30k queries and report results that serve show in certain settings we can learn a faithful interpretable ranker.

Jaspreet Singh, Zeon Trevor Fernando, Saniya Chawla

In addition to user-generated content, Open Educational Resources are increasingly made available on the Web by several institutions and organizations with the aim of being re-used. Nevertheless, it is still difficult for users to find appropriate resources for specific learning scenarios among the vast amount offered on the Web. Our goal is to give users the opportunity to search for authentic resources from the Web and reuse them in a learning context. The LearnWeb-OER platform enhances collaborative searching and sharing of educational resources providing specific means and facilities for education. In the following, we provide a description of the functionalities that support users in collaboratively collecting, selecting, annotating and discussing search results and learning resources.