arXiv subjects

Ponnurangam Kumaraguru

Publications and source records attributed to Ponnurangam Kumaraguru.

At least 37 records · Page 2Linked to original sources

arXiv2025

Structured Definitions and Segmentations for Legal Reasoning in LLMs: A Study on Indian Legal Data

Large Language Models (LLMs), trained on extensive datasets from the web, exhibit remarkable general reasoning skills. Despite this, they often struggle in specialized areas like law, mainly because they lack domain-specific pretraining. The legal field presents unique challenges, as legal documents are generally long and intricate, making it hard for models to process the full text efficiently. Previous studies have examined in-context approaches to address the knowledge gap, boosting model performance in new domains without full domain alignment. In our paper, we analyze model behavior on legal tasks by conducting experiments in three areas: (i) reorganizing documents based on rhetorical roles to assess how structured information affects long context processing and model decisions, (ii) defining rhetorical roles to familiarize the model with legal terminology, and (iii) emulating the step-by-step reasoning of courts regarding rhetorical roles to enhance model reasoning. These experiments are conducted in a zero-shot setting across three Indian legal judgment prediction datasets. Our results reveal that organizing data or explaining key legal terms significantly boosts model performance, with a minimum increase of ~1.5% and a maximum improvement of 4.36% in F1 score compared to the baseline.

cs.CL↗

arXiv2025

SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models

Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer photovoltaic farms. As renewable energy is highly intermittent, building accurate solar irradiance forecasting systems is essential for efficient grid management and enabling the ongoing proliferation of solar energy, which is crucial to achieve the United Nations' net zero goals. In this work, we propose SPIRIT, a novel approach leveraging foundation models for solar irradiance forecasting, making it applicable to newer solar installations. Our approach outperforms state-of-the-art models in zero-shot transfer learning by about 70%, enabling effective performance at new locations without relying on any historical data. Further improvements in performance are achieved through fine-tuning, as more location-specific data becomes available. These findings are supported by statistical significance, further validating our approach. SPIRIT represents a pivotal step towards rapid, scalable, and adaptable solar forecasting solutions, advancing the integration of renewable energy into global power systems.

cs.LG↗

arXiv2025

TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows, multi-agent LLM systems are increasingly used to solve problems collaboratively. However, safety and security of these systems remains largely under-explored. Existing benchmarks and datasets predominantly focus on single-agent settings, failing to capture the unique vulnerabilities of multi-agent dynamics and co-ordination. To address this gap, we introduce $\textbf{T}$hreats and $\textbf{A}$ttacks in $\textbf{M}$ulti-$\textbf{A}$gent $\textbf{S}$ystems ($\textbf{TAMAS}$), a benchmark designed to evaluate the robustness and safety of multi-agent LLM systems. TAMAS includes five distinct scenarios comprising 300 adversarial instances across six attack types and 211 tools, along with 100 harmless tasks. We assess system performance across ten backbone LLMs and three agent interaction configurations from Autogen and CrewAI frameworks, highlighting critical challenges and failure modes in current multi-agent deployments. Furthermore, we introduce Effective Robustness Score (ERS) to assess the tradeoff between safety and task effectiveness of these frameworks. Our findings show that multi-agent systems are highly vulnerable to adversarial attacks, underscoring the urgent need for stronger defenses. TAMAS provides a foundation for systematically studying and improving the safety of multi-agent LLM systems.

cs.MA↗

arXiv2025

Adapting Multilingual Models to Code-Mixed Tasks via Model Merging

We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP. Starting from a multilingual base model, we: (i) perform continued pre-training (CPT) on unlabeled code-mixed text to obtain an adapted checkpoint, (ii) merge checkpoint with the base model, and (iii) fine-tune (FT) on the downstream task data. We evaluate our approach for sentence classification (sentiment and hate speech) task in English-Hindi (En-Hi) and English-Spanish (En-Es) using XLM-R and Llama-3.2-1B models. Our results show that merged models consistently outperform full fine-tuning and CPT->FT. We observe gains of 2--5 points in F1 over full fine-tuning and ~1-2 points over CPT->FT, indicating that unlabeled data is leveraged more effectively via merging than via CPT alone. Zero-/few-shot prompting with larger LLMs (e.g., Llama-3.3-70B) lags behind fine-tuned and merged checkpoints, underscoring limits of in-context learning for code-mixed inputs. We further test cross-pair transfer by training on En-Hi and evaluating on En-Ta and En-Ml: merged checkpoints transfer more strongly than monolingual-English baselines (e.g., TV/TIES variants reaching 0.65-0.68 F1 vs 0.61-0.63 for full fine-tuning), suggesting that code-mixed knowledge is a more reliable substrate for low-resource pairs. We conclude with adaptation recipes matched to common data regimes (labeled only; labeled+unlabeled; transfer-only) and discuss limitations and scaling considerations for broader tasks and larger models.

cs.CL↗

arXiv2025

What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages

How similar are model outputs across languages? In this work, we study this question using a recently proposed model similarity metric $κ_p$ applied to 20 languages and 47 subjects in GlobalMMLU. Our analysis reveals that a model's responses become increasingly consistent across languages as its size and capability grow. Interestingly, models exhibit greater cross-lingual consistency within themselves than agreement with other models prompted in the same language. These results highlight not only the value of $κ_p$ as a practical tool for evaluating multilingual reliability, but also its potential to guide the development of more consistent multilingual systems.

cs.CL↗

arXiv2025

LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision

Curating high-quality, domain-specific datasets is a major bottleneck for deploying robust vision systems, requiring complex trade-offs between data quality, diversity, and cost when researching vast, unlabeled data lakes. We introduce Labeling Copilot, the first data curation deep research agent for computer vision. A central orchestrator agent, powered by a large multimodal language model, uses multi-step reasoning to execute specialized tools across three core capabilities: (1) Calibrated Discovery sources relevant, in-distribution data from large repositories; (2) Controllable Synthesis generates novel data for rare scenarios with robust filtering; and (3) Consensus Annotation produces accurate labels by orchestrating multiple foundation models via a novel consensus mechanism incorporating non-maximum suppression and voting. Our large-scale validation proves the effectiveness of Labeling Copilot's components. The Consensus Annotation module excels at object discovery: on the dense COCO dataset, it averages 14.2 candidate proposals per image-nearly double the 7.4 ground-truth objects-achieving a final annotation mAP of 37.1%. On the web-scale Open Images dataset, it navigated extreme class imbalance to discover 903 new bounding box categories, expanding its capability to over 1500 total. Concurrently, our Calibrated Discovery tool, tested at a 10-million sample scale, features an active learning strategy that is up to 40x more computationally efficient than alternatives with equivalent sample efficiency. These experiments validate that an agentic workflow with optimized, scalable tools provides a robust foundation for curating industrial-scale datasets.

cs.CV↗

arXiv2025

SEMMA: A Semantic Aware Knowledge Graph Foundation Model

Knowledge Graph Foundation Models (KGFMs) have shown promise in enabling zero-shot reasoning over unseen graphs by learning transferable patterns. However, most existing KGFMs rely solely on graph structure, overlooking the rich semantic signals encoded in textual attributes. We introduce SEMMA, a dual-module KGFM that systematically integrates transferable textual semantics alongside structure. SEMMA leverages Large Language Models (LLMs) to enrich relation identifiers, generating semantic embeddings that subsequently form a textual relation graph, which is fused with the structural component. Across 54 diverse KGs, SEMMA outperforms purely structural baselines like ULTRA in fully inductive link prediction. Crucially, we show that in more challenging generalization settings, where the test-time relation vocabulary is entirely unseen, structural methods collapse while SEMMA is 2x more effective. Our findings demonstrate that textual semantics are critical for generalization in settings where structure alone fails, highlighting the need for foundation models that unify structural and linguistic signals in knowledge reasoning.

cs.CL↗

arXiv2025

Ketto and the Science of Giving: A Data-Driven Investigation of Crowdfunding for India

The main goal of this paper is to investigate an up and coming crowdfunding platform used to raise funds for social causes in India called Ketto. Despite the growing usage of this platform, there is insufficient understanding in terms of why users choose this platform when there are other popular platforms such as GoFundMe. Using a dataset comprising of 119,493 Ketto campaigns, our research conducts an in-depth investigation into different aspects of how the campaigns on Ketto work with a specific focus on medical campaigns, which make up the largest percentage of social causes in the dataset. We also perform predictive modeling to identify the factors that contribute to the success of campaigns on this platform. We use several features such as the campaign metadata, description, geolocation, donor behaviors, and campaign-related features to learn about the platform and its components. Our results suggest that majority of the campaigns for medical causes seek funds to address chronic health conditions, yet medical campaigns have the least success rate. Most of the campaigns originate from the most populous states and major metropolitan cities in India. Our analysis also indicates that factors such as online engagement on the platform in terms of the number of comments, duration of the campaign, and frequent updates on a campaign positively influence the funds being raised. Overall, this preliminary work sheds light on the importance of investigating various dynamics around crowdfunding for India-focused community-driven needs.

cs.SI↗

arXiv2025

Freeze and Reveal: Exposing Modality Bias in Vision-Language Models

Vision Language Models achieve impressive multi-modal performance but often inherit gender biases from their training data. This bias might be coming from both the vision and text modalities. In this work, we dissect the contributions of vision and text backbones to these biases by applying targeted debiasing using Counterfactual Data Augmentation and Task Vector methods. Inspired by data-efficient approaches in hate-speech classification, we introduce a novel metric, Degree of Stereotypicality and a corresponding debiasing method, Data Augmentation Using Degree of Stereotypicality - DAUDoS, to reduce bias with minimal computational cost. We curate a gender annotated dataset and evaluate all methods on VisoGender benchmark to quantify improvements and identify dominant source of bias. Our results show that CDA reduces the gender gap by 6% and DAUDoS by 3% but using only one-third of the data. Both methods also improve the model's ability to correctly identify gender in images by 3%, with DAUDoS achieving this improvement using only almost one-third of training data. From our experiment's, we observed that CLIP's vision encoder is more biased whereas PaliGemma2's text encoder is more biased. By identifying whether bias stems more from vision or text encoders, our work enables more targeted and effective bias mitigation strategies in future multi-modal systems.

cs.CV↗

arXiv2025

Long-context Non-factoid Question Answering in Indic Languages

Question Answering (QA) tasks, which involve extracting answers from a given context, are relatively straightforward for modern Large Language Models (LLMs) when the context is short. However, long contexts pose challenges due to the quadratic complexity of the self-attention mechanism. This challenge is compounded in Indic languages, which are often low-resource. This study explores context-shortening techniques, including Open Information Extraction (OIE), coreference resolution, Answer Paragraph Selection (APS), and their combinations, to improve QA performance. Compared to the baseline of unshortened (long) contexts, our experiments on four Indic languages (Hindi, Tamil, Telugu, and Urdu) demonstrate that context-shortening techniques yield an average improvement of 4\% in semantic scores and 47\% in token-level scores when evaluated on three popular LLMs without fine-tuning. Furthermore, with fine-tuning, we achieve an average increase of 2\% in both semantic and token-level scores. Additionally, context-shortening reduces computational overhead. Explainability techniques like LIME and SHAP reveal that when the APS model confidently identifies the paragraph containing the answer, nearly all tokens within the selected text receive high relevance scores. However, the study also highlights the limitations of LLM-based QA systems in addressing non-factoid questions, particularly those requiring reasoning or debate. Moreover, verbalizing OIE-generated triples does not enhance system performance. These findings emphasize the potential of context-shortening techniques to improve the efficiency and effectiveness of LLM-based QA systems, especially for low-resource languages. The source code and resources are available at https://github.com/ritwikmishra/IndicGenQA.

cs.CL↗

arXiv2025

Great Models Think Alike and this Undermines AI Oversight

As Language Model (LM) capabilities advance, evaluating and supervising them at scale is getting harder for humans. There is hope that other language models can automate both these tasks, which we refer to as ''AI Oversight''. We study how model similarity affects both aspects of AI oversight by proposing Chance Adjusted Probabilistic Agreement (CAPA): a metric for LM similarity based on overlap in model mistakes. Using CAPA, we first show that LLM-as-a-judge scores favor models similar to the judge, generalizing recent self-preference results. Then, we study training on LM annotations, and find complementary knowledge between the weak supervisor and strong student model plays a crucial role in gains from ''weak-to-strong generalization''. As model capabilities increase, it becomes harder to find their mistakes, and we might defer more to AI oversight. However, we observe a concerning trend -- model mistakes are becoming more similar with increasing capabilities, pointing to risks from correlated failures. Our work underscores the importance of reporting and correcting for model similarity, especially in the emerging paradigm of AI oversight.

cs.LG↗

arXiv2025

A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks

Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distributed (i.i.d.) assumption, adversarial manipulations or incorrect data can propagate to other data points through message passing, which deteriorates the model's performance. To allow model developers to remove the adverse effects of manipulated entities from a trained GNN, we study the recently formulated problem of Corrective Unlearning. We find that current graph unlearning methods fail to unlearn the effect of manipulations even when the whole manipulated set is known. We introduce a new graph unlearning method, Cognac, which can unlearn the effect of the manipulation set even when only 5% of it is identified. It recovers most of the performance of a strong oracle with fully corrected training data, even beating retraining from scratch without the deletion set while being 8x more efficient. We hope our work assists GNN developers in mitigating harmful effects caused by issues in real-world data, post-training. Our code is publicly available at https://github.com/cognac-gnn-unlearning/corrective-unlearning-for-gnns

cs.LG↗

arXiv2025

Representation Surgery: Theory and Practice of Affine Steering

Language models often exhibit undesirable behavior, e.g., generating toxic or gender-biased text. In the case of neural language models, an encoding of the undesirable behavior is often present in the model's representations. Thus, one natural (and common) approach to prevent the model from exhibiting undesirable behavior is to steer the model's representations in a manner that reduces the probability of it generating undesirable text. This paper investigates the formal and empirical properties of steering functions, i.e., transformation of the neural language model's representations that alter its behavior. First, we derive two optimal, in the least-squares sense, affine steering functions under different constraints. Our theory provides justification for existing approaches and offers a novel, improved steering approach. Second, we offer a series of experiments that demonstrate the empirical effectiveness of the methods in mitigating bias and reducing toxic generation.

cs.LG↗

arXiv2025

MetaGMT: Improving Actionable Interpretability of Graph Multilinear Networks via Meta-Learning Filtration

The growing adoption of Graph Neural Networks (GNNs) in high-stakes domains like healthcare and finance demands reliable explanations of their decision-making processes. While inherently interpretable GNN architectures like Graph Multi-linear Networks (GMT) have emerged, they remain vulnerable to generating explanations based on spurious correlations, potentially undermining trust in critical applications. We present MetaGMT, a meta-learning framework that enhances explanation fidelity through a novel bi-level optimization approach. We demonstrate that MetaGMT significantly improves both explanation quality (AUC-ROC, Precision@K) and robustness to spurious patterns, across BA-2Motifs, MUTAG, and SP-Motif benchmarks. Our approach maintains competitive classification accuracy while producing more faithful explanations (with an increase up to 8% of Explanation ROC on SP-Motif 0.5) compared to baseline methods. These advancements in interpretability could enable safer deployment of GNNs in sensitive domains by (1) facilitating model debugging through more reliable explanations, (2) supporting targeted retraining when biases are identified, and (3) enabling meaningful human oversight. By addressing the critical challenge of explanation reliability, our work contributes to building more trustworthy and actionable GNN systems for real-world applications.

cs.LG↗

arXiv2025

Analyzing Patterns and Influence of Advertising in Print Newspapers

This paper investigates advertising practices in print newspapers across India using a novel data-driven approach. We develop a pipeline employing image processing and OCR techniques to extract articles and advertisements from digital versions of print newspapers with high accuracy. Applying this methodology to five popular newspapers that span multiple regions and three languages, English, Hindi, and Telugu, we assembled a dataset of more than 12,000 editions containing several hundred thousand advertisements. Collectively, these newspapers reach a readership of over 100 million people. Using this extensive dataset, we conduct a comprehensive analysis to answer key questions about print advertising: who advertises, what they advertise, when they advertise, where they place their ads, and how they advertise. Our findings reveal significant patterns, including the consistent level of print advertising over the past six years despite declining print circulation, the overrepresentation of company ads on prominent pages, and the disproportionate revenue contributed by government ads. Furthermore, we examine whether advertising in a newspaper influences the coverage an advertiser receives. Through regression analyses on coverage volume and sentiment, we find strong evidence supporting this hypothesis for corporate advertisers. The results indicate a clear trend where increased advertising correlates with more favorable and extensive media coverage, a relationship that remains robust over time and across different levels of advertiser popularity.

cs.CY↗

arXiv2025

COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models

Large Language Models (LLMs) often inherit biases from the web data they are trained on, which contains stereotypes and prejudices. Current methods for evaluating and mitigating these biases rely on bias-benchmark datasets. These benchmarks measure bias by observing an LLM's behavior on biased statements. However, these statements lack contextual considerations of the situations they try to present. To address this, we introduce a contextual reliability framework, which evaluates model robustness to biased statements by considering the various contexts in which they may appear. We develop the Context-Oriented Bias Indicator and Assessment Score (COBIAS) to measure a biased statement's reliability in detecting bias, based on the variance in model behavior across different contexts. To evaluate the metric, we augmented 2,291 stereotyped statements from two existing benchmark datasets by adding contextual information. We show that COBIAS aligns with human judgment on the contextual reliability of biased statements (Spearman's $ρ= 0.65, p = 3.4 * 10^{-60}$) and can be used to create reliable benchmarks, which would assist bias mitigation works.

cs.CL↗

arXiv2025

From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences

Current computational approaches for analysing or generating code-mixed sentences do not explicitly model ``naturalness'' or ``acceptability'' of code-mixed sentences, but rely on training corpora to reflect distribution of acceptable code-mixed sentences. Modelling human judgement for the acceptability of code-mixed text can help in distinguishing natural code-mixed text and enable quality-controlled generation of code-mixed text. To this end, we construct Cline - a dataset containing human acceptability judgements for English-Hindi~(en-hi) code-mixed text. Cline is the largest of its kind with 16,642 sentences, consisting of samples sourced from two sources: synthetically generated code-mixed text and samples collected from online social media. Our analysis establishes that popular code-mixing metrics such as CMI, Number of Switch Points, Burstines, which are used to filter/curate/compare code-mixed corpora have low correlation with human acceptability judgements, underlining the necessity of our dataset. Experiments using Cline demonstrate that simple Multilayer Perceptron (MLP) models when trained solely using code-mixing metrics as features are outperformed by fine-tuned pre-trained Multilingual Large Language Models (MLLMs). Specifically, among Encoder models XLM-Roberta and Bernice outperform IndicBERT across different configurations. Among Encoder-Decoder models, mBART performs better than mT5, however Encoder-Decoder models are not able to outperform Encoder-only models. Decoder-only models perform the best when compared to all other MLLMS, with Llama 3.2 - 3B models outperforming similarly sized Qwen, Phi models. Comparison with zero and fewshot capabilitites of ChatGPT show that MLLMs fine-tuned on larger data outperform ChatGPT, providing scope for improvement in code-mixed tasks. Zero-shot transfer from En-Hi to En-Te acceptability judgments are better than random baselines.

cs.CL↗

arXiv2025

Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling

Function calling is a complex task with widespread applications in domains such as information retrieval, software engineering and automation. For example, a query to book the shortest flight from New York to London on January 15 requires identifying the correct parameters to generate accurate function calls. Large Language Models (LLMs) can automate this process but are computationally expensive and impractical in resource-constrained settings. In contrast, Small Language Models (SLMs) can operate efficiently, offering faster response times, and lower computational demands, making them potential candidates for function calling on edge devices. In this exploratory empirical study, we evaluate the efficacy of SLMs in generating function calls across diverse domains using zero-shot, few-shot, and fine-tuning approaches, both with and without prompt injection, while also providing the finetuned models to facilitate future applications. Furthermore, we analyze the model responses across a range of metrics, capturing various aspects of function call generation. Additionally, we perform experiments on an edge device to evaluate their performance in terms of latency and memory usage, providing useful insights into their practical applicability. Our findings show that while SLMs improve from zero-shot to few-shot and perform best with fine-tuning, they struggle significantly with adhering to the given output format. Prompt injection experiments further indicate that the models are generally robust and exhibit only a slight decline in performance. While SLMs demonstrate potential for the function call generation task, our results also highlight areas that need further refinement for real-time functioning.

cs.AI↗