arXiv subjects

Saptarshi Ghosh

Publications and source records attributed to Saptarshi Ghosh.

At least 19 recordsLinked to original sources

arXiv2026

Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation

In many real-world scenarios, encountering continual shifts in domain during inference is very common. Consequently, continual test-time adaptation (CTTA) techniques leveraging a teacher-student framework have gained prominence, allowing models to adapt continuously even after deployment. In such a framework, a weight-averaged mean teacher is used to produce pseudo-labels from test data for self-training. The mean teacher gets updated as an exponential moving average of the student parameters using a high value of momentum that is kept fixed even if different distributions of test data are encountered. To combat the resulting drift of the model, we propose a novel controlled teacher adaptation methodology that dynamically sets a proper momentum value depending on the quality of the incoming data. Additionally, we estimate class prototypes from the source pretrained model to help align the target data as they come in. Importantly, our method does not require access to source data or its statistics at any stage of the pipeline, making it truly source-free. We perform extensive experiments on benchmark datasets to demonstrate that our approach outperforms different state-of-the-art adaptation frameworks, many of which require access to source data.

cs.LG↗

arXiv2026

A 32-channel event-based bio-signal analog front-end with adaptive delta and pulse frequency encoding

Low-power event-based Analog Front-Ends (AFEs) are essential for building efficient, end-to-end neuromorphic signal processing systems. In this paper, we present an event-based AFE Application-Specific Integrated Circuit (ASIC) optimized for biomedical signal acquisition and encoding. The chip features 32 independently programmable input channels with dual-mode encoding mechanism outputs, comprising Pulse Frequency Modulation (PFM) and adaptive Asynchronous Delta Modulator (aADM) circuits. The aADM encoder provides an auto-scaling mechanism that adapts the encoding data-rate based on the input signal envelope in real-time, enabling very high data compression for low-power information transmission. This approach paves the way toward adaptive wireless communication of neural signals for on-line processing in brain-computer interfaces. Fabricated in a 180 nm CMOS process, the proposed ASIC offers a highly configurable interface compatible with state-of-the-art Spiking Neural Network (SNN) neuromorphic processors.

cs.AR↗

arXiv2026

A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs

In recent times, Large Language Models (LLMs) are increasingly being used for legal case judgement summarization. Most prior works have tried traditional extractive and abstractive summarization of case judgements. However, hybrid or extractive-abstractive techniques have not been explored much. In this work, we propose a novel tree-of-thoughts inspired extractive-abstractive summarization approach for legal judgement summarization. We conduct experiments using two popular LLMs, DeepSeek and LLama, and compare among extractive, abstractive and extractive-abstractive summarization. Our experiments show that the proposed extractive-abstractive prompt provides better summaries compared to other types of LLM prompts.

cs.CL↗

arXiv2026

Peeking Inside LLMs: Leveraging Internal Artifacts of LLMs for Enhancing Reliability in Legal Classification

Large Language Models (LLMs) are increasingly being adopted in the legal domain. However, despite their strong performance, LLMs are prone to generating incorrect or hallucinated outputs, raising serious concerns about their reliability in high-stakes domains such as law. Detecting the correctness of responses of LLM-based systems is therefore a critical challenge. In this work, we explore the potential of leveraging internal artifacts of LLM to detect the correctness of their predictions in legal-domain classification tasks. We develop approaches that utilize features derived from these internal artifacts to build downstream classifiers capable of identifying incorrect LLM outputs. We evaluate our approach on two representative legal classification tasks: bail decision prediction and statute violation prediction. Our experimental results demonstrate that LLMs' internal artifacts are reliable indicators for detecting incorrect predictions in legal classification tasks, and can be applied to enhance the reliability of LLM-based classification systems.

cs.CL↗

arXiv2026

Cross-Lingual Steering for Figurative Language Generation

Multilingual large language models can generate figurative language, but whether the internal signals driving this behavior are language-specific or reusable across languages is unclear. Using activation steering as a probe, we estimate a direction for a figurative category from figurative--literal activation differences in one language and apply it during generation. Across five figurative categories, six languages, and four multilingual LLMs, these directions steer reliably within their own language, most robustly for metaphor and simile. More importantly, they transfer across languages: a direction learned in one increases the target behavior when applied to another, with German among the most receptive targets. Going further, directions assembled from other languages can match or even surpass a target language's own native direction, while removing this shared component weakens native steering. Together, these results provide direct evidence of a reusable but target-dependent cross-lingual signal for figurative generation.

cs.CL↗

arXiv2026

Evaluating the Impact of Verbal Multiword Expressions on Machine Translation

Verbal multiword expressions (VMWEs) remain difficult for machine translation because their meanings are often not recoverable from their component words. In this study, we analyze the impact of three VMWE categories -- verbal idioms, verb-particle constructions, and light verb constructions -- on machine translation quality from English to multiple languages. Using both established multiword expression datasets and standard machine translation datasets, we evaluate how state-of-the-art translation systems handle these expressions. Our experimental results consistently show that VMWEs negatively affect translation quality, with deeper analysis indicating that this degradation is primarily attributable to the VMWE itself rather than general sentence-level difficulty. We release our code and evaluation framework to test new MT systems for the community.

cs.CL↗

arXiv2026

MetFuse: Figurative Fusion between Metonymy and Metaphor

Metonymy and metaphor often co-occur in natural language, yet computational work has studied them largely in isolation. We introduce a framework that transforms a literal sentence into three figurative variants: metonymic, metaphoric, and hybrid. Using this framework, we construct MetFuse, the first dedicated dataset of figurative fusion between metonymy and metaphor, containing 1,000 human-verified meaning-aligned quadruplets totaling 4,000 sentences. Extrinsic experiments on eight existing benchmarks show that augmenting training data with MetFuse consistently improves both metonymy and metaphor classification, with hybrid examples yielding the largest gains on metonymy tasks. Using this dataset, we also analyze how the presence of one figurative type impacts another. Our findings show that both human annotators and large language models better identify metonymy in hybrid sentences than in metonymy-only sentences, demonstrating that the presence of a metaphor makes a metonymic noun more explicit. Our dataset is publicly available at: https://github.com/cincynlp/MetFuse.

cs.CL↗

arXiv2026

Exploring Concreteness Through a Figurative Lens

Static concreteness ratings are widely used in NLP, yet a word's concreteness can shift with context, especially in figurative language such as metaphor, where common concrete nouns can take abstract interpretations. While such shifts are evident from context, it remains unclear how LLMs understand concreteness internally. We conduct a layer-wise and geometric analysis of LLM hidden representations across four model families, examining how models distinguish literal vs figurative uses of the same noun and how concreteness is organized in representation space. We find that LLMs separate literal and figurative usage in early layers, and that mid-to-late layers compress concreteness into a one-dimensional direction that is consistent across models. Finally, we show that this geometric structure is practically useful: a single concreteness direction supports efficient figurative-language classification and enables training-free steering of generation toward more literal or more figurative rewrites.

cs.CL↗

arXiv2026

NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System

Court Judgment Prediction and Explanation (CJPE) aims to predict a judicial decision and provide a legally grounded explanation for a given case based on the facts, legal issues, arguments, cited statutes, and relevant precedents. For such systems to be practically useful in judicial or legal research settings, they must not only achieve high predictive performance but also generate transparent and structured legal reasoning that aligns with established judicial practices. In this work, we present NyayaMind, an open-source framework designed to enable transparent and scalable legal reasoning for the Indian judiciary. The proposed framework integrates retrieval, reasoning, and verification mechanisms to emulate the structured decision-making process typically followed in courts. Specifically, NyayaMind consists of two main components: a Retrieval Module and a Prediction Module. The Retrieval Module employs a RAG pipeline to identify legally relevant statutes and precedent cases from large-scale legal corpora, while the Prediction Module utilizes reasoning-oriented LLMs fine-tuned for the Indian legal domain to generate structured outputs including issues, arguments, rationale, and the final decision. Our extensive results and expert evaluation demonstrate that NyayaMind significantly improves the quality of explanation and evidence alignment compared to existing CJPE approaches, providing a promising step toward trustworthy AI-assisted legal decision support systems.

cs.CL↗

arXiv2026

Performance Comparison of IBN orchestration using LLM and SLMs

The evolution of both 5G and 6G networks is driving the advancement of fully autonomous network management, placing Intent-Based Networking at the centre of this transformation. This paper introduces a novel framework for 5G and 6G IBN orchestration that leverages a stateful, hierarchical multi-agent architecture to achieve full automation using both SLMs and LLMs. Both models have been evaluated for translation accuracy using metrics such as BLEU, METEOR, and ROUGE-L, as well as computational complexity. Experimental results show that both models exhibit similar accuracy. However, result shows that SLMs can improve the overall completion speed of the IBN lifecycle by 20%.

cs.NI↗

arXiv2026

Benchmarking the Energy Savings with Speculative Decoding Strategies

Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper presents a comprehensive survey of energy requirements of speculative decoding strategies, with detailed analysis on how various factors -- model size and family, speculative decoding strategies, and dataset characteristics -- influence the energy optimizations.

cs.LG↗

arXiv2026

Advantages of Domain Knowledge Injection for Legal Document Summarization: A Case Study on Summarizing Indian Court Judgments in English and Hindi

Summarizing Indian legal court judgments is a complex task not only due to the intricate language and unstructured nature of the legal texts, but also since a large section of the Indian population does not understand the complex English in which legal text is written, thus requiring summaries in Indian languages. In this study, we aim to improve the summarization of Indian legal text to generate summaries in both English and Hindi (the most widely spoken Indian language), by injecting domain knowledge into diverse summarization models. We propose a framework to enhance extractive neural summarization models by incorporating domain-specific pre-trained encoders tailored for legal texts. Further, we explore the injection of legal domain knowledge into generative models (including Large Language Models) through continual pre-training on large legal corpora in English and Hindi. Our proposed approaches achieve statistically significant improvements in both English-to-English and English-to-Hindi Indian legal document summarization, as measured by standard evaluation metrics, factual consistency metrics, and legal domain-specific metrics. Furthermore, these improvements are validated through domain experts, demonstrating the effectiveness of our approaches.

cs.CL↗

arXiv2026

ILSIC: Corpora for Identifying Indian Legal Statutes from Queries by Laypeople

Legal Statute Identification (LSI) for a given situation is one of the most fundamental tasks in Legal NLP. This task has traditionally been modeled using facts from court judgments as input queries, due to their abundance. However, in practical settings, the input queries are likely to be informal and asked by laypersons, or non-professionals. While a few laypeople LSI datasets exist, there has been little research to explore the differences between court and laypeople data for LSI. In this work, we create ILSIC, a corpus of laypeople queries covering 500+ statutes from Indian law. Additionally, the corpus also contains court case judgements to enable researchers to effectively compare between court and laypeople data for LSI. We conducted extensive experiments on our corpus, including benchmarking over the laypeople dataset using zero and few-shot inference, retrieval-augmented generation and supervised fine-tuning. We observe that models trained purely on court judgements are ineffective during test on laypeople queries, while transfer learning from court to laypeople data can be beneficial in certain scenarios. We also conducted fine-grained analyses of our results in terms of categories of queries and frequency of statutes.

cs.CL↗

arXiv2026

A Computational Approach to Visual Metonymy

Images often communicate more than they literally depict: a set of tools can suggest an occupation and a cultural artifact can suggest a tradition. This kind of indirect visual reference, known as visual metonymy, invites viewers to recover a target concept via associated cues rather than explicit depiction. In this work, we present the first computational investigation of visual metonymy. We introduce a novel pipeline grounded in semiotic theory that leverages large language models and text-to-image models to generate metonymic visual representations. Using this framework, we construct ViMET, the first visual metonymy dataset comprising 2,000 multiple-choice questions to evaluate the cognitive reasoning abilities in multimodal language models. Experimental results on our dataset reveal a significant gap between human performance (86.9%) and state-of-the-art vision-language models (65.9%), highlighting limitations in machines' ability to interpret indirect visual references. Our dataset is publicly available at: https://github.com/cincynlp/ViMET.

cs.CL↗

arXiv2026

Do LLM hallucination detectors suffer from low-resource effect?

LLMs, while outperforming humans in a wide range of tasks, can still fail in unanticipated ways. We focus on two pervasive failure modes: (i) hallucinations, where models produce incorrect information about the world, and (ii) the low-resource effect, where the models show impressive performance in high-resource languages like English but the performance degrades significantly in low-resource languages like Bengali. We study the intersection of these issues and ask: do hallucination detectors suffer from the low-resource effect? We conduct experiments on five tasks across three domains (factual recall, STEM, and Humanities). Experiments with four LLMs and three hallucination detectors reveal a curious finding: As expected, the task accuracies in low-resource languages experience large drops (compared to English). However, the drop in detectors' accuracy is often several times smaller than the drop in task accuracy. Our findings suggest that even in low-resource languages, the internal mechanisms of LLMs might encode signals about their uncertainty. Further, the detectors are robust within language (even for non-English) and in multilingual setups, but not in cross-lingual settings without in-language supervision.

cs.CL↗

arXiv2025

Unraveling the Nature of HAWC J1844-034 with Fermi-LAT Data Analysis and Multi-wavelength Modeling

The extended ultra-high-energy (UHE) gamma-ray source HAWC J1844-034 is closely associated with two other sources, HAWC J1843-032 and HWC J1846-025. Moreover, other gamma-ray observatories like H.E.S.S., LHAASO, and Tibet AS$_γ$ have detected UHE gamma-ray sources whose spatial positions coincide with the position of HAWC J1844-034. The UHE gamma-ray data from several observatories help analyse the spectral features of this source in detail at TeV energies. Of the four pulsars near HAWC J1844-034, PSR J1844-0346 is closest to it and possibly supplies the cosmic-ray leptons to power this source. We have analysed the Fermi-LAT data to explore this source's morphology and identify its spectral feature in the Fermi-LAT energy band. After removing the contribution of the pulsar to the gamma-ray spectral energy distribution by pulsar phased analysis, we have obtained upper limits on the photon flux and identified the GeV counterpart PS J1844.2-0342 in the Fermi-LAT energy band with more than 5$σ$ significance, which may be a pulsar wind nebula (PWN). Finally, the multi-wavelength spectral energy distribution is modeled, assuming HAWC J1844-034 is a PWN.

astro-ph.HE↗

arXiv2025

IL-PCSR: Legal Corpus for Prior Case and Statute Retrieval

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.

cs.CL↗

arXiv2025

Utilising Large Language Models for Generating Effective Counter Arguments to Anti-Vaccine Tweets

In an era where public health is increasingly influenced by information shared on social media, combatting vaccine skepticism and misinformation has become a critical societal goal. Misleading narratives around vaccination have spread widely, creating barriers to achieving high immunisation rates and undermining trust in health recommendations. While efforts to detect misinformation have made significant progress, the generation of real time counter-arguments tailored to debunk such claims remains an insufficiently explored area. In this work, we explore the capabilities of LLMs to generate sound counter-argument rebuttals to vaccine misinformation. Building on prior research in misinformation debunking, we experiment with various prompting strategies and fine-tuning approaches to optimise counter-argument generation. Additionally, we train classifiers to categorise anti-vaccine tweets into multi-labeled categories such as concerns about vaccine efficacy, side effects, and political influences allowing for more context aware rebuttals. Our evaluation, conducted through human judgment, LLM based assessments, and automatic metrics, reveals strong alignment across these methods. Our findings demonstrate that integrating label descriptions and structured fine-tuning enhances counter-argument effectiveness, offering a promising approach for mitigating vaccine misinformation at scale.

cs.CL↗