Ashutosh Modi

Arnav Kapoor, Mudit Dhawan, Anmol Goel et al.

Many populous countries including India are burdened with a considerable backlog of legal cases. Development of automated systems that could process legal documents and augment legal practitioners can mitigate this. However, there is a dearth of high-quality corpora that is needed to develop such data-driven systems. The problem gets even more pronounced in the case of low resource languages such as Hindi. In this resource paper, we introduce the Hindi Legal Documents Corpus (HLDC), a corpus of more than 900K legal documents in Hindi. Documents are cleaned and structured to enable the development of downstream applications. Further, as a use-case for the corpus, we introduce the task of bail prediction. We experiment with a battery of models and propose a Multi-Task Learning (MTL) based model for the same. MTL models use summarization as an auxiliary task along with bail prediction as the main task. Experiments with different models are indicative of the need for further research in this area. We release the corpus and model implementation code with this paper: https://github.com/Exploration-Lab/HLDC

Abhinav Joshi, Areeb Ahmad, Umang Pandey et al.

Text-based games provide a framework for developing natural language understanding and commonsense knowledge about the world in reinforcement learning based agents. Existing text-based environments often rely on fictional situations and characters to create a gaming framework and are far from real-world scenarios. In this paper, we introduce ScriptWorld: a text-based environment for teaching agents about real-world daily chores and hence imparting commonsense knowledge. To the best of our knowledge, it is the first interactive text-based gaming framework that consists of daily real-world human activities designed using scripts dataset. We provide gaming environments for 10 daily activities and perform a detailed analysis of the proposed environment. We develop RL-based baseline models/agents to play the games in Scriptworld. To understand the role of language models in such environments, we leverage features obtained from pre-trained language models in the RL agents. Our experiments show that prior knowledge obtained from a pre-trained language model helps to solve real-world text-based gaming environments. We release the environment via Github: https://github.com/Exploration-Lab/ScriptWorld

Abhinav Joshi, Ashwani Bhat, Ayush Jain et al.

Emotions are an inherent part of human interactions, and consequently, it is imperative to develop AI systems that understand and recognize human emotions. During a conversation involving various people, a person's emotions are influenced by the other speaker's utterances and their own emotional state over the utterances. In this paper, we propose COntextualized Graph Neural Network based Multimodal Emotion recognitioN (COGMEN) system that leverages local information (i.e., inter/intra dependency between speakers) and global information (context). The proposed model uses Graph Neural Network (GNN) based architecture to model the complex dependencies (local and global information) in a conversation. Our model gives state-of-the-art (SOTA) results on IEMOCAP and MOSEI datasets, and detailed ablation experiments show the importance of modeling information at both levels.

Ashutosh Modi, Prathamesh Kalamkar, Saurabh Karn et al.

In populous countries, pending legal cases have been growing exponentially. There is a need for developing NLP-based techniques for processing and automatically understanding legal documents. To promote research in the area of Legal NLP we organized the shared task LegalEval - Understanding Legal Texts at SemEval 2023. LegalEval task has three sub-tasks: Task-A (Rhetorical Roles Labeling) is about automatically structuring legal documents into semantically coherent units, Task-B (Legal Named Entity Recognition) deals with identifying relevant entities in a legal document and Task-C (Court Judgement Prediction with Explanation) explores the possibility of automatically predicting the outcome of a legal case along with providing an explanation for the prediction. In total 26 teams (approx. 100 participants spread across the world) submitted systems paper. In each of the sub-tasks, the proposed systems outperformed the baselines; however, there is a lot of scope for improvement. This paper describes the tasks, and analyzes techniques proposed by various teams.

Ashutosh Dwivedi, Pradhyumna Lavania, Ashutosh Modi

Etiquettes are an essential ingredient of day-to-day interactions among people. Moreover, etiquettes are region-specific, and etiquettes in one region might contradict those in other regions. In this paper, we propose EtiCor, an Etiquettes Corpus, having texts about social norms from five different regions across the globe. The corpus provides a test bed for evaluating LLMs for knowledge and understanding of region-specific etiquettes. Additionally, we propose the task of Etiquette Sensitivity. We experiment with state-of-the-art LLMs (Delphi, Falcon40B, and GPT-3.5). Initial results indicate that LLMs, mostly fail to understand etiquettes from regions from non-Western world.

Abhinav Joshi, Naman Gupta, Jinang Shah et al.

A real-world application or setting involves interaction between different modalities (e.g., video, speech, text). In order to process the multimodal information automatically and use it for an end application, Multimodal Representation Learning (MRL) has emerged as an active area of research in recent times. MRL involves learning reliable and robust representations of information from heterogeneous sources and fusing them. However, in practice, the data acquired from different sources are typically noisy. In some extreme cases, a noise of large magnitude can completely alter the semantics of the data leading to inconsistencies in the parallel multimodal data. In this paper, we propose a novel method for multimodal representation learning in a noisy environment via the generalized product of experts technique. In the proposed method, we train a separate network for each modality to assess the credibility of information coming from that modality, and subsequently, the contribution from each modality is dynamically varied while estimating the joint distribution. We evaluate our method on two challenging benchmarks from two diverse domains: multimodal 3D hand-pose estimation and multimodal surgical video segmentation. We attain state-of-the-art performance on both benchmarks. Our extensive quantitative and qualitative evaluations show the advantages of our method compared to previous approaches.

Abhinav Joshi, Shounak Paul, Akshat Sharma et al.

Legal systems worldwide are inundated with exponential growth in cases and documents. There is an imminent need to develop NLP and ML techniques for automatically processing and understanding legal documents to streamline the legal system. However, evaluating and comparing various NLP models designed specifically for the legal domain is challenging. This paper addresses this challenge by proposing IL-TUR: Benchmark for Indian Legal Text Understanding and Reasoning. IL-TUR contains monolingual (English, Hindi) and multi-lingual (9 Indian languages) domain-specific tasks that address different aspects of the legal system from the point of view of understanding and reasoning over Indian legal documents. We present baseline models (including LLM-based) for each task, outlining the gap between models and the ground truth. To foster further research in the legal domain, we create a leaderboard (available at: https://exploration-lab.github.io/IL-TUR/) where the research community can upload and compare legal text understanding systems.

Abhinav Joshi, Akshat Sharma, Sai Kiran Tanikella et al.

The task of Prior Case Retrieval (PCR) in the legal domain is about automatically citing relevant (based on facts and precedence) prior legal cases in a given query case. To further promote research in PCR, in this paper, we propose a new large benchmark (in English) for the PCR task: IL-PCR (Indian Legal Prior Case Retrieval) corpus. Given the complex nature of case relevance and the long size of legal documents, BM25 remains a strong baseline for ranking the cited prior documents. In this work, we explore the role of events in legal case retrieval and propose an unsupervised retrieval method-based pipeline U-CREAT (Unsupervised Case Retrieval using Events Extraction). We find that the proposed unsupervised retrieval method significantly increases performance compared to BM25 and makes retrieval faster by a considerable margin, making it applicable to real-time case retrieval systems. Our proposed system is generic, we show that it generalizes across two different legal systems (Indian and Canadian), and it shows state-of-the-art performance on the benchmarks for both the legal systems (IL-PCR and COLIEE corpora).

Abhinav Joshi, Susmit Agrawal, Ashutosh Modi

Sign languages are the primary means of communication for many hard-of-hearing people worldwide. Recently, to bridge the communication gap between the hard-of-hearing community and the rest of the population, several sign language translation datasets have been proposed to enable the development of statistical sign language translation systems. However, there is a dearth of sign language resources for the Indian sign language. This resource paper introduces ISLTranslate, a translation dataset for continuous Indian Sign Language (ISL) consisting of 31k ISL-English sentence/phrase pairs. To the best of our knowledge, it is the largest translation dataset for continuous Indian Sign Language. We provide a detailed analysis of the dataset. To validate the performance of existing end-to-end Sign language to spoken language translation systems, we benchmark the created dataset with a transformer-based model for ISL translation.

Abhinav Joshi, Romit Mohanty, Mounika Kanakanti et al.

Indian Sign Language has limited resources for developing machine learning and data-driven approaches for automated language processing. Though text/audio-based language processing techniques have shown colossal research interest and tremendous improvements in the last few years, Sign Languages still need to catch up due to the need for more resources. To bridge this gap, in this work, we propose iSign: a benchmark for Indian Sign Language (ISL) Processing. We make three primary contributions to this work. First, we release one of the largest ISL-English datasets with more than 118K video-sentence/phrase pairs. To the best of our knowledge, it is the largest sign language dataset available for ISL. Second, we propose multiple NLP-specific tasks (including SignVideo2Text, SignPose2Text, Text2Pose, Word Prediction, and Sign Semantics) and benchmark them with the baseline models for easier access to the research community. Third, we provide detailed insights into the proposed benchmarks with a few linguistic insights into the workings of ISL. We streamline the evaluation of Sign Language processing, addressing the gaps in the NLP research community for Sign Languages. We release the dataset, tasks, and models via the following website: https://exploration-lab.github.io/iSign/

Ashwani Bhat, Ashutosh Modi

Predicting emotions expressed in text is a well-studied problem in the NLP community. Recently there has been active research in extracting the cause of an emotion expressed in text. Most of the previous work has done causal emotion entailment in documents. In this work, we propose neural models to extract emotion cause span and entailment in conversations. For learning such models, we use RECCON dataset, which is annotated with cause spans at the utterance level. In particular, we propose MuTEC, an end-to-end Multi-Task learning framework for extracting emotions, emotion cause, and entailment in conversations. This is in contrast to existing baseline models that use ground truth emotions to extract the cause. MuTEC performs better than the baselines for most of the data folds provided in the dataset.

Sanjeet Singh, Shreya Gupta, Niralee Gupta et al.

The consequences of a healthcare data breach can be devastating for the patients, providers, and payers. The average financial impact of a data breach in recent months has been estimated to be close to USD 10 million. This is especially significant for healthcare organizations in India that are managing rapid digitization while still establishing data governance procedures that align with the letter and spirit of the law. Computer-based systems for de-identification of personal information are vulnerable to data drift, often rendering them ineffective in cross-institution settings. Therefore, a rigorous assessment of existing de-identification against local health datasets is imperative to support the safe adoption of digital health initiatives in India. Using a small set of de-identified patient discharge summaries provided by an Indian healthcare institution, in this paper, we report the nominal performance of de-identification algorithms (based on language models) trained on publicly available non-Indian datasets, pointing towards a lack of cross-institutional generalization. Similarly, experimentation with off-the-shelf de-identification systems reveals potential risks associated with the approach. To overcome data scarcity, we explore generating synthetic clinical reports (using publicly available and Indian summaries) by performing in-context learning over Large Language Models (LLMs). Our experiments demonstrate the use of generated reports as an effective strategy for creating high-performing de-identification systems with good generalization capabilities.

Divyaksh Shukla, Ashutosh Modi

Machine unlearning aims to remove the influence of specific training data from a model while preserving reliable behavior on the remaining data, making reliable prediction and uncertainty estimation essential for evaluation. Calibration is commonly used as a proxy for reliability in language models, but low calibration error does not necessarily imply reliable decision rules, as models may rely on spurious correlations while remaining well calibrated. We investigate this gap in generative language models using the multiple-choice question-answering evaluation protocol on the TOFU benchmark, measuring probabilistic reliability with calibration metrics (ECE, MCE, Brier) and decision-rule reliability via attribution-based shortcut detection with Integrated Gradients and Local Mutual Information. We find that fine-tuned models achieve low calibration error (ECE ~ 0.04) compared to pretrained models (ECE > 0.5), and models after unlearning retain similarly low calibration despite reduced accuracy on the forget split, while attribution analysis shows increased reliance on correlation-based tokens. These results demonstrate that good calibration can coexist with shortcut-based decision rules after unlearning, extending the reliability paradox to the machine unlearning setting.

Abhinav Joshi, Areeb Ahmad, Ashutosh Modi

Large Language Models (LLMs) have demonstrated inherent calibration capabilities, where predicted probabilities align well with correctness, despite prior findings that deep neural networks are often overconfident. Recent studies have linked this behavior to specific components in the final layer, such as entropy neurons and the unembedding matrix null space. In this work, we provide a complementary perspective by investigating how calibration evolves throughout the network depth. Analyzing multiple open-weight models on the MMLU benchmark, we uncover a distinct confidence correction phase in the upper/later layers, where model confidence is actively recalibrated after decision certainty has been reached. Furthermore, we identify a low-dimensional calibration direction in the residual stream whose perturbation significantly improves calibration metrics (ECE and MCE) without harming accuracy. Our findings suggest that calibration is a distributed phenomenon, shaped throughout the network forward pass, not just in its final projection, providing new insights into how confidence-regulating mechanisms operate within LLMs.

Abhinav Joshi, Vaibhav Sharma, Sanjeet Singh et al.

Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.

Shounak Paul, Dhananjay Ghumare, Pawan Goyal et al.

Identifying/retrieving relevant statutes and prior cases/precedents for a given legal situation are common tasks exercised by law practitioners. Researchers to date have addressed the two tasks independently, thus developing completely different datasets and models for each task; however, both retrieval tasks are inherently related, e.g., similar cases tend to cite similar statutes (due to similar factual situation). In this paper, we address this gap. We propose IL-PCR (Indian Legal corpus for Prior Case and Statute Retrieval), which is a unique corpus that provides a common testbed for developing models for both the tasks (Statute Retrieval and Precedent Retrieval) that can exploit the dependence between the two. We experiment extensively with several baseline models on the tasks, including lexical models, semantic models and ensemble based on GNNs. Further, to exploit the dependence between the two tasks, we develop an LLM-based re-ranking approach that gives the best performance.

Muhammad Farid Adilazuarda, Sagnik Mukherjee, Pradhyumna Lavania et al.

We present a survey of more than 90 recent papers that aim to study cultural representation and inclusion in large language models (LLMs). We observe that none of the studies explicitly define "culture, which is a complex, multifaceted concept; instead, they probe the models on some specially designed datasets which represent certain aspects of "culture". We call these aspects the proxies of culture, and organize them across two dimensions of demographic and semantic proxies. We also categorize the probing methods employed. Our analysis indicates that only certain aspects of ``culture,'' such as values and objectives, have been studied, leaving several other interesting and important facets, especially the multitude of semantic domains (Thompson et al., 2020) and aboutness (Hershcovich et al., 2022), unexplored. Two other crucial gaps are the lack of robustness of probing techniques and situated studies on the impact of cultural mis- and under-representation in LLM-based applications.

Tafazzul Nadeem, Bhavik Shangari, Manish Rai et al.

Professionals working in technical domain typically hand-draw (on whiteboard, paper, etc.) technical diagrams (e.g., flowcharts, block diagrams, etc.) during discussions; however, if they want to edit these later, it needs to be drawn from scratch. Modern day VLMs have made tremendous progress in image understanding but they struggle when it comes to understanding technical diagrams. One way to overcome this problem is to fine-tune on real world hand-drawn images, but it is not practically possible to generate large number of such images. In this paper, we introduce a large synthetically generated corpus (reflective of real world images) for training VLMs and subsequently evaluate VLMs on a smaller corpus of hand-drawn images (with the help of humans). We introduce several new self-supervision tasks for training and perform extensive experiments with various baseline models and fine-tune Llama 3.2 11B-instruct model on synthetic images on these tasks to obtain LLama-VL-TUG, which significantly improves the ROUGE-L performance of Llama 3.2 11B-instruct by 2.14x and achieves the best all-round performance across all baseline models. On real-world images, human evaluation reveals that we achieve minimum compilation errors across all baselines in 7 out of 8 diagram types and improve the average F1 score of Llama 3.2 11B-instruct by 6.97x.

Abhinav Joshi, Shaswati Saha, Divyaksh Shukla et al. · microsoft-research

Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best efforts during the data pre-processing stage while training the LLMs, they may pick some undesirable information such as personally identifiable information (PII). Consequently, in recent times research in the area of Machine Unlearning (MUL) has become active, the main idea is to force LLMs to forget (unlearn) certain information (e.g., PII) without suffering from performance loss on regular tasks. In this work, we examine the robustness of the existing MUL techniques for their ability to enable leakage-proof forgetting in LLMs. In particular, we examine the effect of data transformation on forgetting, i.e., is an unlearned LLM able to recall forgotten information if there is a change in the format of the input? Our findings on the TOFU dataset highlight the necessity of using diverse data formats to quantify unlearning in LLMs more reliably.

Abhinav Joshi, Areeb Ahmad, Ashutosh Modi

Large Language Models (LLMs) have shown state-of-the-art performance in a variety of tasks, including arithmetic and reasoning; however, to gauge the intellectual capabilities of LLMs, causal reasoning has become a reliable proxy for validating a general understanding of the mechanics and intricacies of the world similar to humans. Previous works in natural language processing (NLP) have either focused on open-ended causal reasoning via causal commonsense reasoning (CCR) or framed a symbolic representation-based question answering for theoretically backed-up analysis via a causal inference engine. The former adds an advantage of real-world grounding but lacks theoretically backed-up analysis/validation, whereas the latter is far from real-world grounding. In this work, we bridge this gap by proposing the COLD (Causal reasOning in cLosed Daily activities) framework, which is built upon human understanding of daily real-world activities to reason about the causal nature of events. We show that the proposed framework facilitates the creation of enormous causal queries (~ 9 million) and comes close to the mini-turing test, simulating causal reasoning to evaluate the understanding of a daily real-world task. We evaluate multiple LLMs on the created causal queries and find that causal reasoning is challenging even for activities trivial to humans. We further explore (the causal reasoning abilities of LLMs) using the backdoor criterion to determine the causal strength between events.

Shubham Patel, Divyaksh Shukla, Ashutosh Modi

This paper presents our approach for the SemEval-2024 Task 10: Emotion Discovery and Reasoning its Flip in Conversations. For the Emotion Recognition in Conversations (ERC) task, we utilize a masked-memory network along with speaker participation. We propose a transformer-based speaker-centric model for the Emotion Flip Reasoning (EFR) task. We also introduce Probable Trigger Zone, a region of the conversation that is more likely to contain the utterances causing the emotion to flip. For sub-task 3, the proposed approach achieves a 5.9 (F1 score) improvement over the task baseline. The ablation study results highlight the significance of various design choices in the proposed method.

Abhinav Joshi, Areeb Ahmad, Divyaksh Shukla et al.

Commonsense reasoning deals with the implicit knowledge that is well understood by humans and typically acquired via interactions with the world. In recent times, commonsense reasoning and understanding of various LLMs have been evaluated using text-based tasks. In this work, we argue that a proxy of this understanding can be maintained as a graphical structure that can further help to perform a rigorous evaluation of commonsense reasoning abilities about various real-world activities. We create an annotation scheme for capturing this implicit knowledge in the form of a graphical structure for 37 daily human activities. We find that the created resource can be used to frame an enormous number of commonsense queries (~ 10^{17}), facilitating rigorous evaluation of commonsense reasoning in LLMs. Moreover, recently, the remarkable performance of LLMs has raised questions about whether these models are truly capable of reasoning in the wild and, in general, how reasoning occurs inside these models. In this resource paper, we bridge this gap by proposing design mechanisms that facilitate research in a similar direction. Our findings suggest that the reasoning components are localized in LLMs that play a prominent role in decision-making when prompted with a commonsense query.

Udvas Basak, Rajarshi Dutta, Shivam Pandey et al.

This paper describes our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness. The challenge is focused on automatically detecting the degree of relatedness between pairs of sentences for 14 languages including both high and low-resource Asian and African languages. Our team participated in two subtasks consisting of Track A: supervised and Track B: unsupervised. This paper focuses on a BERT-based contrastive learning and similarity metric based approach primarily for the supervised track while exploring autoencoders for the unsupervised track. It also aims on the creation of a bigram relatedness corpus using negative sampling strategy, thereby producing refined word embeddings.

Shreyasi Mandal, Ashutosh Modi

Large Language models (LLMs) have demonstrated state-of-the-art performance in various natural language processing (NLP) tasks across multiple domains, yet they are prone to shortcut learning and factual inconsistencies. This research investigates LLMs' robustness, consistency, and faithful reasoning when performing Natural Language Inference (NLI) on breast cancer Clinical Trial Reports (CTRs) in the context of SemEval 2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. We examine the reasoning capabilities of LLMs and their adeptness at logical problem-solving. A comparative analysis is conducted on pre-trained language models (PLMs), GPT-3.5, and Gemini Pro under zero-shot settings using Retrieval-Augmented Generation (RAG) framework, integrating various reasoning chains. The evaluation yields an F1 score of 0.69, consistency of 0.71, and a faithfulness score of 0.90 on the test dataset.

Shreenaga Chikoti, Shrey Mehta, Ashutosh Modi

Memes are one of the most popular types of content used in an online disinformation campaign. They are primarily effective on social media platforms since they can easily reach many users. Memes in a disinformation campaign achieve their goal of influencing the users through several rhetorical and psychological techniques, such as causal oversimplification, name-calling, and smear. The SemEval 2024 Task 4 \textit{Multilingual Detection of Persuasion Technique in Memes} on identifying such techniques in the memes is divided across three sub-tasks: ($\mathbf{1}$) Hierarchical multi-label classification using only textual content of the meme, ($\mathbf{2}$) Hierarchical multi-label classification using both, textual and visual content of the meme and ($\mathbf{3}$) Binary classification of whether the meme contains a persuasion technique or not using it's textual and visual content. This paper proposes an ensemble of Class Definition Prediction (CDP) and hyperbolic embeddings-based approaches for this task. We enhance meme classification accuracy and comprehensiveness by integrating HypEmo's hierarchical label embeddings (Chen et al., 2023) and a multi-task learning framework for emotion prediction. We achieve a hierarchical F1-score of 0.60, 0.67, and 0.48 on the respective sub-tasks.

Gagan Raj Gupta, Anshul Kumar, Manish Rai et al.

Large Language Models (LLMs) have emerged as powerful tools for automating complex reasoning and decision-making tasks. In telecommunications, they hold the potential to transform network optimization, automate troubleshooting, enhance customer support, and ensure regulatory compliance. However, their deployment in telecom is hindered by domain-specific challenges that demand specialized adaptation. To overcome these challenges and to accelerate the adaptation of LLMs for telecom, we propose MM-Telco, a comprehensive suite of multimodal benchmarks and models tailored for the telecom domain. The benchmark introduces various tasks (both text based and image based) that address various practical real-life use cases such as network operations, network management, improving documentation quality, and retrieval of relevant text and images. Further, we perform baseline experiments with various LLMs and VLMs. The models fine-tuned on our dataset exhibit a significant boost in performance. Our experiments also help analyze the weak areas in the working of current state-of-art multimodal LLMs, thus guiding towards further development and research.

Abhinav Joshi, Divyanshu Bhatt, Ashutosh Modi

Large Language Models (LLMs) show strong generalization across diverse tasks, yet the internal decision-making processes behind their predictions remain opaque. In this work, we study the geometry of hidden representations in LLMs through the lens of \textit{intrinsic dimension} (ID), focusing specifically on decision-making dynamics in a multiple-choice question answering (MCQA) setting. We perform a large-scale study, with 28 open-weight transformer models and estimate ID across layers using multiple estimators, while also quantifying per-layer performance on MCQA tasks. Our findings reveal a consistent ID pattern across models: early layers operate on low-dimensional manifolds, middle layers expand this space, and later layers compress it again, converging to decision-relevant representations. Together, these results suggest LLMs implicitly learn to project linguistic inputs onto structured, low-dimensional manifolds aligned with task-specific decisions, providing new geometric insights into how generalization and reasoning emerge in language models.

Areeb Ahmad, Abhinav Joshi, Ashutosh Modi

Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron layers (MLPs) (the building blocks of a transformer architecture) as indivisible units, overlooking possibilities of functional substructure learned within them. In this work, we introduce a more fine-grained perspective that decomposes these components into orthogonal singular directions, revealing superposed and independent computations within a single head or MLP. We validate our perspective on widely used standard tasks like Indirect Object Identification (IOI), Gender Pronoun (GP), and Greater Than (GT), showing that previously identified canonical functional heads, such as the name mover, encode multiple overlapping subfunctions aligned with distinct singular directions. Nodes in a computational graph, that are previously identified as circuit elements show strong activation along specific low-rank directions, suggesting that meaningful computations reside in compact subspaces. While some directions remain challenging to interpret fully, our results highlight that transformer computations are more distributed, structured, and compositional than previously assumed. This perspective opens new avenues for fine-grained mechanistic interpretability and a deeper understanding of model internals.

Deepali Mishra, Chaklam Silpasuwanchai, Ashutosh Modi et al.

Medical Visual Question Answering (MedVQA) is a promising tool to assist radiologists by automating medical image interpretation through question answering. Despite advances in models and datasets, MedVQA's integration into clinical workflows remains limited. This study systematically reviews 68 publications (2018-2024) and surveys 50 clinicians from India and Thailand to examine MedVQA's practical utility, challenges, and gaps. Following the Arksey and O'Malley scoping review framework, we used a two-pronged approach: (1) reviewing studies to identify key concepts, advancements, and research gaps in radiology workflows, and (2) surveying clinicians to capture their perspectives on MedVQA's clinical relevance. Our review reveals that nearly 60% of QA pairs are non-diagnostic and lack clinical relevance. Most datasets and models do not support multi-view, multi-resolution imaging, EHR integration, or domain knowledge, features essential for clinical diagnosis. Furthermore, there is a clear mismatch between current evaluation metrics and clinical needs. The clinician survey confirms this disconnect: only 29.8% consider MedVQA systems highly useful. Key concerns include the absence of patient history or domain knowledge (87.2%), preference for manually curated datasets (51.1%), and the need for multi-view image support (78.7%). Additionally, 66% favor models focused on specific anatomical regions, and 89.4% prefer dialogue-based interactive systems. While MedVQA shows strong potential, challenges such as limited multimodal analysis, lack of patient context, and misaligned evaluation approaches must be addressed for effective clinical integration.

Divyaksh Shukla, Ritesh Baviskar, Dwijesh Gohil et al.

Discourse parsing is an important task useful for NLU applications such as summarization, machine comprehension, and emotion recognition. The current discourse parsing datasets based on conversations consists of written English dialogues restricted to a single domain. In this resource paper, we introduce CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversations. The corpus (code-mixed in Hindi and English) has both audio and transcribed text and is annotated with nine discourse relations. We experiment with various SoTA baseline models; the poor performance of SoTA models highlights the challenges of multi-domain code-mixed corpus, pointing towards the need for developing better models for such realistic settings.

Ashutosh Dwivedi, Siddhant Shivdutt Singh, Ashutosh Modi

In recent years, researchers have started analyzing the cultural sensitivity of LLMs. In this respect, Etiquettes have been an active area of research. Etiquettes are region-specific and are an essential part of the culture of a region; hence, it is imperative to make LLMs sensitive to etiquettes. However, there needs to be more resources in evaluating LLMs for their understanding and bias with regard to etiquettes. In this resource paper, we introduce EtiCor++, a corpus of etiquettes worldwide. We introduce different tasks for evaluating LLMs for knowledge about etiquettes across various regions. Further, we introduce various metrics for measuring bias in LLMs. Extensive experimentation with LLMs shows inherent bias towards certain regions.

Harsh Bihany, Shubham Patel, Ashutosh Modi

Large Language Models have shown remarkable capabilities in the NLP domain. Their effectiveness can mainly be attributed to their ability to adapt to an array of downstream tasks. However, generally, full fine-tuning is a computationally expensive job. To mitigate this, many techniques have been developed that prime efficiency, a prominent one being Low-Rank Adaptation (LoRA). However, LoRA and its variants employ re-parametrized additive updates. In this paper, we propose Low-Rank Multiplicative Adaptation (LoRMA), which shifts the paradigm of additive updates to a richer space of matrix multiplicative transformations. We tackle challenges such as computational complexity and rank bottleneck of matrix multiplication by effectively re-ordering operations and introducing rank inflation strategies. We conduct extensive experiments to demonstrate the effectiveness of our approach in terms of various evaluation metrics.

Rahul Kumar, Amar Raja Dibbu, Shrutendra Harsola et al.

Several large-scale datasets (e.g., WikiSQL, Spider) for developing natural language interfaces to databases have recently been proposed. These datasets cover a wide breadth of domains but fall short on some essential domains, such as finance and accounting. Given that accounting databases are used worldwide, particularly by non-technical people, there is an imminent need to develop models that could help extract information from accounting databases via natural language queries. In this resource paper, we aim to fill this gap by proposing a new large-scale Text-to-SQL dataset for the accounting and financial domain: BookSQL. The dataset consists of 100k natural language queries-SQL pairs, and accounting databases of 1 million records. We experiment with and analyze existing state-of-the-art models (including GPT-4) for the Text-to-SQL task on BookSQL. We find significant performance gaps, thus pointing towards developing more focused models for this domain.

Prathamesh Kalamkar, Aman Tiwari, Astha Agarwal et al.

In populous countries, pending legal cases have been growing exponentially. There is a need for developing techniques for processing and organizing legal documents. In this paper, we introduce a new corpus for structuring legal documents. In particular, we introduce a corpus of legal judgment documents in English that are segmented into topical and coherent parts. Each of these parts is annotated with a label coming from a list of pre-defined Rhetorical Roles. We develop baseline models for automatically predicting rhetorical roles in a legal document based on the annotated corpus. Further, we show the application of rhetorical roles to improve performance on the tasks of summarization and legal judgment prediction. We release the corpus and baseline model code along with the paper.

Harsh Agarwal, Keshav Bansal, Abhinav Joshi et al.

Emotion Recognition in Conversations (ERC) is an important and active research area. Recent work has shown the benefits of using multiple modalities (e.g., text, audio, and video) for the ERC task. In a conversation, participants tend to maintain a particular emotional state unless some stimuli evokes a change. There is a continuous ebb and flow of emotions in a conversation. Inspired by this observation, we propose a multimodal ERC model and augment it with an emotion-shift component that improves performance. The proposed emotion-shift component is modular and can be added to any existing multimodal ERC model (with a few modifications). We experiment with different variants of the model, and results show that the inclusion of emotion shift signal helps the model to outperform existing models for ERC on MOSEI and IEMOCAP datasets.

Vijit Malik, Rishabh Sanjay, Shouvik Kumar Guha et al.

Legal documents are unstructured, use legal jargon, and have considerable length, making them difficult to process automatically via conventional text processing techniques. A legal document processing system would benefit substantially if the documents could be segmented into coherent information units. This paper proposes a new corpus of legal documents annotated (with the help of legal experts) with a set of 13 semantically coherent units labels (referred to as Rhetorical Roles), e.g., facts, arguments, statute, issue, precedent, ruling, and ratio. We perform a thorough analysis of the corpus and the annotations. For automatically segmenting the legal documents, we experiment with the task of rhetorical role prediction: given a document, predict the text segments corresponding to various roles. Using the created corpus, we experiment extensively with various deep learning-based baseline models for the task. Further, we develop a multitask learning (MTL) based deep model with document rhetorical role label shift as an auxiliary task for segmenting a legal document. The proposed model shows superior performance over the existing models. We also experiment with model performance in the case of domain transfer and model distillation techniques to see the model performance in limited data conditions.

Gargi Singh, Dhanajit Brahma, Piyush Rai et al.

In this paper, we propose a new framework for fine-grained emotion prediction in the text through emotion definition modeling. Our approach involves a multi-task learning framework that models definitions of emotions as an auxiliary task while being trained on the primary task of emotion prediction. We model definitions using masked language modeling and class definition prediction tasks. Our models outperform existing state-of-the-art for fine-grained emotion dataset GoEmotions. We further show that this trained model can be used for transfer learning on other benchmark datasets in emotion prediction with varying emotion label sets, domains, and sizes. The proposed models outperform the baselines on transfer learning experiments demonstrating the generalization capability of the models.

Ishika Singh, Gargi Singh, Ashutosh Modi

Recently, text world games have been proposed to enable artificial agents to understand and reason about real-world scenarios. These text-based games are challenging for artificial agents, as it requires an understanding of and interaction using natural language in a partially observable environment. Agents observe the environment via textual descriptions designed to be challenging enough for even human players. Past approaches have not paid enough attention to the language understanding capability of the proposed agents. Typically, these approaches train from scratch, an agent that learns both textual representations and the gameplay online during training using a temporal loss function. Given the sample-inefficiency of RL approaches, it is inefficient to learn rich enough textual representations to be able to understand and reason using the textual observation in such a complicated game environment setting. In this paper, we improve the semantic understanding of the agent by proposing a simple RL with LM framework where we use transformer-based language models with Deep RL models. We perform a detailed study of our framework to demonstrate how our model outperforms all existing agents on the popular game, Zork1, to achieve a score of 44.7, which is 1.6 higher than the state-of-the-art model. Overall, our proposed approach outperforms 4 games out of the 14 text-based games, while performing comparable to the state-of-the-art models on the remaining games.

Vijit Malik, Rishabh Sanjay, Shubham Kumar Nigam et al.

An automated system that could assist a judge in predicting the outcome of a case would help expedite the judicial process. For such a system to be practically useful, predictions by the system should be explainable. To promote research in developing such a system, we introduce ILDC (Indian Legal Documents Corpus). ILDC is a large corpus of 35k Indian Supreme Court cases annotated with original court decisions. A portion of the corpus (a separate test set) is annotated with gold standard explanations by legal experts. Based on ILDC, we propose the task of Court Judgment Prediction and Explanation (CJPE). The task requires an automated system to predict an explainable outcome of a case. We experiment with a battery of baseline models for case predictions and propose a hierarchical occlusion based model for explainability. Our best prediction model has an accuracy of 78% versus 94% for human legal experts, pointing towards the complexity of the prediction task. The analysis of explanations by the proposed algorithm reveals a significant difference in the point of view of the algorithm and legal experts for explaining the judgments, pointing towards scope for future research.

Pradip Swarnakar, Ashutosh Modi

Climate change is a burning issue of our time, with the Sustainable Development Goal (SDG) 13 of the United Nations demanding global climate action. Realizing the urgency, in 2015 in Paris, world leaders signed an agreement committing to taking voluntary action to reduce carbon emissions. However, the scale, magnitude, and climate action processes vary globally, especially between developed and developing countries. Therefore, from parliament to social media, the debates and discussions on climate change gather data from wide-ranging sources essential to the policy design and implementation. The downside is that we do not currently have the mechanisms to pool the worldwide dispersed knowledge emerging from the structured and unstructured data sources. The paper thematically discusses how NLP techniques could be employed in climate policy research and contribute to society's good at large. In particular, we exemplify symbiosis of NLP and Climate Policy Research via four methodologies. The first one deals with the major topics related to climate policy using automated content analysis. We investigate the opinions (sentiments) of major actors' narratives towards climate policy in the second methodology. The third technique explores the climate actors' beliefs towards pro or anti-climate orientation. Finally, we discuss developing a Climate Knowledge Graph. The present theme paper further argues that creating a knowledge platform would help in the formulation of a holistic climate policy and effective climate action. Such a knowledge platform would integrate the policy actors' varied opinions from different social sectors like government, business, civil society, and the scientific community. The research outcome will add value to effective climate action because policymakers can make informed decisions by looking at the diverse public opinion on a comprehensive platform.

Aditya Jindal, Ankur Gupta, Jaya Srivastava et al.

Recently, there has been an interest in factual verification and prediction over structured data like tables and graphs. To circumvent any false news incident, it is necessary to not only model and predict over structured data efficiently but also to explain those predictions. In this paper, as part of the SemEval-2021 Task 9, we tackle the problem of fact verification and evidence finding over tabular data. There are two subtasks. Given a table and a statement/fact, subtask A determines whether the statement is inferred from the tabular data, and subtask B determines which cells in the table provide evidence for the former subtask. We make a comparison of the baselines and state-of-the-art approaches over the given SemTabFact dataset. We also propose a novel approach CellBERT to solve evidence finding as a form of the Natural Language Inference task. We obtain a 3-way F1 score of 0.69 on subtask A and an F1 score of 0.65 on subtask B.

Shashank Shailabh, Sajal Chaurasia, Ashutosh Modi

Research in Natural Language Processing is making rapid advances, resulting in the publication of a large number of research papers. Finding relevant research papers and their contribution to the domain is a challenging problem. In this paper, we address this challenge via the SemEval 2021 Task 11: NLPContributionGraph, by developing a system for a research paper contributions-focused knowledge graph over Natural Language Processing literature. The task is divided into three sub-tasks: extracting contribution sentences that show important contributions in the research article, extracting phrases from the contribution sentences, and predicting the information units in the research article together with triplet formation from the phrases. The proposed system is agnostic to the subject domain and can be applied for building a knowledge graph for any area. We found that transformer-based language models can significantly improve existing techniques and utilized the SciBERT-based model. Our first sub-task uses Bidirectional LSTM (BiLSTM) stacked on top of SciBERT model layers, while the second sub-task uses Conditional Random Field (CRF) on top of SciBERT with BiLSTM. The third sub-task uses a combined SciBERT based neural approach with heuristics for information unit prediction and triplet formation from the phrases. Our system achieved F1 score of 0.38, 0.63 and 0.76 in end-to-end pipeline testing, phrase extraction testing and triplet extraction testing respectively.

Rohan Gupta, Jay Mundra, Deepak Mahajan et al.

In this work, we present our approach for solving the SemEval 2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). The task is a sentence pair classification problem where the goal is to detect whether a given word common to both the sentences evokes the same meaning. We submit systems for both the settings - Multilingual (the pair's sentences belong to the same language) and Cross-Lingual (the pair's sentences belong to different languages). The training data is provided only in English. Consequently, we employ cross-lingual transfer techniques. Our approach employs fine-tuning pre-trained transformer-based language models, like ELECTRA and ALBERT, for the English task and XLM-R for all other tasks. To improve these systems' performance, we propose adding a signal to the word to be disambiguated and augmenting our data by sentence pair reversal. We further augment the dataset provided to us with WiC, XL-WiC and SemCor 3.0. Using ensembles, we achieve strong performance in the Multilingual task, placing first in the EN-EN and FR-FR sub-tasks. For the Cross-Lingual setting, we employed translate-test methods and a zero-shot method, using our multilingual models, with the latter performing slightly better.

Archit Bansal, Abhay Kaushik, Ashutosh Modi

In this work, we present our approach and findings for SemEval-2021 Task 5 - Toxic Spans Detection. The task's main aim was to identify spans to which a given text's toxicity could be attributed. The task is challenging mainly due to two constraints: the small training dataset and imbalanced class distribution. Our paper investigates two techniques, semi-supervised learning and learning with Self-Adjusting Dice Loss, for tackling these challenges. Our submitted system (ranked ninth on the leader board) consisted of an ensemble of various pre-trained Transformer Language Models trained using either of the above-proposed techniques.

Abhishek Mittal, Ashutosh Modi

This paper describes our system for Task 4 of SemEval-2021: Reading Comprehension of Abstract Meaning (ReCAM). We participated in all subtasks where the main goal was to predict an abstract word missing from a statement. We fine-tuned the pre-trained masked language models namely BERT and ALBERT and used an Ensemble of these as our submitted system on Subtask 1 (ReCAM-Imperceptibility) and Subtask 2 (ReCAM-Nonspecificity). For Subtask 3 (ReCAM-Intersection), we submitted the ALBERT model as it gives the best results. We tried multiple approaches and found that Masked Language Modeling(MLM) based approach works the best.

Akash Gangwar, Sabhay Jain, Shubham Sourav et al.

This paper presents the system for SemEval 2021 Task 8 (MeasEval). MeasEval is a novel span extraction, classification, and relation extraction task focused on finding quantities, attributes of these quantities, and additional information, including the related measured entities, properties, and measurement contexts. Our submitted system, which placed fifth (team rank) on the leaderboard, consisted of SciBERT with [CLS] token embedding and CRF layer on top. We were also placed first in Quantity (tied) and Unit subtasks, second in MeasuredEntity, Modifier and Qualifies subtasks, and third in Qualifier subtask.

Neil Rajiv Shirude, Sagnik Mukherjee, Tushar Shandhilya et al.

This paper describes our contribution to SemEval 2021 Task 1: Lexical Complexity Prediction. In our approach, we leverage the ELECTRA model and attempt to mirror the data annotation scheme. Although the task is a regression task, we show that we can treat it as an aggregation of several classification and regression models. This somewhat counter-intuitive approach achieved an MAE score of 0.0654 for Sub-Task 1 and MAE of 0.0811 on Sub-Task 2. Additionally, we used the concept of weak supervision signals from Gloss-BERT in our work, and it significantly improved the MAE score in Sub-Task 1.

Aishwarya Gupta, Avik Pal, Bholeshwar Khurana et al.

Humor and Offense are highly subjective due to multiple word senses, cultural knowledge, and pragmatic competence. Hence, accurately detecting humorous and offensive texts has several compelling use cases in Recommendation Systems and Personalized Content Moderation. However, due to the lack of an extensive labeled dataset, most prior works in this domain haven't explored large neural models for subjective humor understanding. This paper explores whether large neural models and their ensembles can capture the intricacies associated with humor/offense detection and rating. Our experiments on the SemEval-2021 Task 7: HaHackathon show that we can develop reasonable humor and offense detection systems with such models. Our models are ranked third in subtask 1b and consistently ranked around the top 33% of the leaderboard for the remaining subtasks.

Aaditya Singh, Shreeshail Hingane, Saim Wani et al.

The task of Emotion-Cause Pair Extraction (ECPE) aims to extract all potential clause-pairs of emotions and their corresponding causes in a document. Unlike the more well-studied task of Emotion Cause Extraction (ECE), ECPE does not require the emotion clauses to be provided as annotations. Previous works on ECPE have either followed a multi-stage approach where emotion extraction, cause extraction, and pairing are done independently or use complex architectures to resolve its limitations. In this paper, we propose an end-to-end model for the ECPE task. Due to the unavailability of an English language ECPE corpus, we adapt the NTCIR-13 ECE corpus and establish a baseline for the ECPE task on this dataset. On this dataset, the proposed method produces significant performance improvements (~6.5 increase in F1 score) over the multi-stage approach and achieves comparable performance to the state-of-the-art methods.

Vijit Malik, Ashwani Bhat, Ashutosh Modi

Deep learning models are susceptible to adversarial examples that have imperceptible perturbations in the original input, resulting in adversarial attacks against these models. Analysis of these attacks on the state of the art transformers in NLP can help improve the robustness of these models against such adversarial inputs. In this paper, we present Adv-OLM, a black-box attack method that adapts the idea of Occlusion and Language Models (OLM) to the current state of the art attack methods. OLM is used to rank words of a sentence, which are later substituted using word replacement strategies. We experimentally show that our approach outperforms other attack methods for several text classification tasks.