arXiv subjects

Tirthankar Ghosal

Publications and source records attributed to Tirthankar Ghosal.

36 records · Page 2Linked to original sources

arXiv2025

Can Large Language Models Unlock Novel Scientific Research Ideas?

The widespread adoption of Large Language Models (LLMs) and publicly available ChatGPT have marked a significant turning point in the integration of Artificial Intelligence (AI) into people's everyday lives. This study examines the ability of Large Language Models (LLMs) to generate future research ideas from scientific papers. Unlike tasks such as summarization or translation, idea generation lacks a clearly defined reference set or structure, making manual evaluation the default standard. However, human evaluation in this setting is extremely challenging ie: it requires substantial domain expertise, contextual understanding of the paper, and awareness of the current research landscape. This makes it time-consuming, costly, and fundamentally non-scalable, particularly as new LLMs are being released at a rapid pace. Currently, there is no automated evaluation metric specifically designed for this task. To address this gap, we propose two automated evaluation metrics: Idea Alignment Score (IAScore) and Idea Distinctness Index. We further conducted human evaluation to assess the novelty, relevance, and feasibility of the generated future research ideas. This investigation offers insights into the evolving role of LLMs in idea generation, highlighting both its capability and limitations. Our work contributes to the ongoing efforts in evaluating and utilizing language models for generating future research ideas. We make our datasets and codes publicly available

cs.CL↗

arXiv2025

Findings of the Third Automatic Minuting (AutoMin) Challenge

This paper presents the third edition of AutoMin, a shared task on automatic meeting summarization into minutes. In 2025, AutoMin featured the main task of minuting, the creation of structured meeting minutes, as well as a new task: question answering (QA) based on meeting transcripts. The minuting task covered two languages, English and Czech, and two domains: project meetings and European Parliament sessions. The QA task focused solely on project meetings and was available in two settings: monolingual QA in English, and cross-lingual QA, where questions were asked and answered in Czech based on English meetings. Participation in 2025 was more limited compared to previous years, with only one team joining the minuting task and two teams participating in QA. However, as organizers, we included multiple baseline systems to enable a comprehensive evaluation of current (2025) large language models (LLMs) on both tasks.

cs.CL↗

arXiv2025

Intelligent Manufacturing Support: Specialized LLMs for Composite Material Processing and Equipment Operation

Engineering educational curriculum and standards cover many material and manufacturing options. However, engineers and designers are often unfamiliar with certain composite materials or manufacturing techniques. Large language models (LLMs) could potentially bridge the gap. Their capacity to store and retrieve data from large databases provides them with a breadth of knowledge across disciplines. However, their generalized knowledge base can lack targeted, industry-specific knowledge. To this end, we present two LLM-based applications based on the GPT-4 architecture: (1) The Composites Guide: a system that provides expert knowledge on composites material and connects users with research and industry professionals who can provide additional support and (2) The Equipment Assistant: a system that provides guidance for manufacturing tool operation and material characterization. By combining the knowledge of general AI models with industry-specific knowledge, both applications are intended to provide more meaningful information for engineers. In this paper, we discuss the development of the applications and evaluate it through a benchmark and two informal user studies. The benchmark analysis uses the Rouge and Bertscore metrics to evaluate our model performance against GPT-4o. The results show that GPT-4o and the proposed models perform similarly or better on the ROUGE and BERTScore metrics. The two user studies supplement this quantitative evaluation by asking experts to provide qualitative and open-ended feedback about our model performance on a set of domain-specific questions. The results of both studies highlight a potential for more detailed and specific responses with the Composites Guide and the Equipment Assistant.

stat.AP↗

arXiv2025

EPIC: Generative AI Platform for Accelerating HPC Operational Data Analytics

We present EPIC, an AI-driven platform designed to augment operational data analytics. EPIC employs a hierarchical multi-agent architecture where a top-level large language model provides query processing, reasoning and synthesis capabilities. These capabilities orchestrate three specialized low-level agents for information retrieval, descriptive analytics, and predictive analytics. This architecture enables EPIC to perform HPC operational analytics on multi-modal data, including text, images, and tabular formats, dynamically and iteratively. EPIC addresses the limitations of existing HPC operational analytics approaches, which rely on static methods that struggle to adapt to evolving analytics tasks and stakeholder demands. Through extensive evaluations on the Frontier HPC system, we demonstrate that EPIC effectively handles complex queries. Using descriptive analytics as a use case, fine-tuned smaller models outperform large state-of-the-art foundation models, achieving up to 26% higher accuracy. Additionally, we achieved 19x savings in LLM operational costs compared to proprietary solutions by employing a hybrid approach that combines large foundational models with fine-tuned local open-weight models.

cs.DB↗

arXiv2025

PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows

Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and peers, and influence scientific outcomes across federated and heterogeneous environments. However, agents can hallucinate or reason incorrectly, propagating errors when one agent's output becomes another's input. Thus, assuring that agents' actions are transparent, traceable, reproducible, and reliable is critical to assess hallucination risks and mitigate their workflow impacts. While provenance techniques have long supported these principles, existing methods fail to capture and relate agent-centric metadata such as prompts, responses, and decisions with the broader workflow context and downstream outcomes. In this paper, we introduce PROV-AGENT, a provenance model that extends W3C PROV and leverages the Model Context Protocol (MCP) and data observability to integrate agent interactions into end-to-end workflow provenance. Our contributions include: (1) a provenance model tailored for agentic workflows, (2) a near real-time, open-source system for capturing agentic provenance, and (3) a cross-facility evaluation spanning edge, cloud, and HPC environments, demonstrating support for critical provenance queries and agent reliability analysis.

cs.DC↗

arXiv2025

A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions

Retrieval-Augmented Generation (RAG) represents a major advancement in natural language processing (NLP), combining large language models (LLMs) with information retrieval systems to enhance factual grounding, accuracy, and contextual relevance. This paper presents a comprehensive systematic review of RAG, tracing its evolution from early developments in open domain question answering to recent state-of-the-art implementations across diverse applications. The review begins by outlining the motivations behind RAG, particularly its ability to mitigate hallucinations and outdated knowledge in parametric models. Core technical components-retrieval mechanisms, sequence-to-sequence generation models, and fusion strategies are examined in detail. A year-by-year analysis highlights key milestones and research trends, providing insight into RAG's rapid growth. The paper further explores the deployment of RAG in enterprise systems, addressing practical challenges related to retrieval of proprietary data, security, and scalability. A comparative evaluation of RAG implementations is conducted, benchmarking performance on retrieval accuracy, generation fluency, latency, and computational efficiency. Persistent challenges such as retrieval quality, privacy concerns, and integration overhead are critically assessed. Finally, the review highlights emerging solutions, including hybrid retrieval approaches, privacy-preserving techniques, optimized fusion strategies, and agentic RAG architectures. These innovations point toward a future of more reliable, efficient, and context-aware knowledge-intensive NLP systems.

cs.CL↗

arXiv2025

AstroMLab 3: Achieving GPT-4o Level Performance in Astronomy with a Specialized 8B-Parameter Large Language Model

AstroSage-Llama-3.1-8B is a domain-specialized natural-language AI assistant tailored for research in astronomy, astrophysics, cosmology, and astronomical instrumentation. Trained on the complete collection of astronomy-related arXiv papers from 2007 to 2024 along with millions of synthetically-generated question-answer pairs and other astronomical literature, AstroSage-Llama-3.1-8B demonstrates remarkable proficiency on a wide range of questions. AstroSage-Llama-3.1-8B scores 80.9% on the AstroMLab-1 benchmark, greatly outperforming all models -- proprietary and open-weight -- in the 8-billion parameter class, and performing on par with GPT-4o. This achievement demonstrates the potential of domain specialization in AI, suggesting that focused training can yield capabilities exceeding those of much larger, general-purpose models. AstroSage-Llama-3.1-8B is freely available, enabling widespread access to advanced AI capabilities for astronomical education and research.

astro-ph.IM↗

arXiv2025

Sparks of Science: Hypothesis Generation Using Structured Paper Data

Generating novel and creative scientific hypotheses is a cornerstone in achieving Artificial General Intelligence. Large language and reasoning models have the potential to aid in the systematic creation, selection, and validation of scientifically informed hypotheses. However, current foundation models often struggle to produce scientific ideas that are both novel and feasible. One reason is the lack of a dedicated dataset that frames Scientific Hypothesis Generation (SHG) as a Natural Language Generation (NLG) task. In this paper, we introduce HypoGen, the first dataset of approximately 5500 structured problem-hypothesis pairs extracted from top-tier computer science conferences structured with a Bit-Flip-Spark schema, where the Bit is the conventional assumption, the Spark is the key insight or conceptual leap, and the Flip is the resulting counterproposal. HypoGen uniquely integrates an explicit Chain-of-Reasoning component that reflects the intellectual process from Bit to Flip. We demonstrate that framing hypothesis generation as conditional language modelling, with the model fine-tuned on Bit-Flip-Spark and the Chain-of-Reasoning (and where, at inference, we only provide the Bit), leads to improvements in the overall quality of the hypotheses. Our evaluation employs automated metrics and LLM judge rankings for overall quality assessment. We show that by fine-tuning on our HypoGen dataset we improve the novelty, feasibility, and overall quality of the generated hypotheses. The HypoGen dataset is publicly available at huggingface.co/datasets/UniverseTBD/hypogen-dr1.

cs.CL↗

arXiv2025

A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models

Hypothesis generation is a fundamental step in scientific discovery, yet it is increasingly challenged by information overload and disciplinary fragmentation. Recent advances in Large Language Models (LLMs) have sparked growing interest in their potential to enhance and automate this process. This paper presents a comprehensive survey of hypothesis generation with LLMs by (i) reviewing existing methods, from simple prompting techniques to more complex frameworks, and proposing a taxonomy that categorizes these approaches; (ii) analyzing techniques for improving hypothesis quality, such as novelty boosting and structured reasoning; (iii) providing an overview of evaluation strategies; and (iv) discussing key challenges and future directions, including multimodal integration and human-AI collaboration. Our survey aims to serve as a reference for researchers exploring LLMs for hypothesis generation.

cs.CL↗

arXiv2024

AstroMLab 1: Who Wins Astronomy Jeopardy!?

We present a comprehensive evaluation of proprietary and open-weights large language models using the first astronomy-specific benchmarking dataset. This dataset comprises 4,425 multiple-choice questions curated from the Annual Review of Astronomy and Astrophysics, covering a broad range of astrophysical topics. Our analysis examines model performance across various astronomical subfields and assesses response calibration, crucial for potential deployment in research environments. Claude-3.5-Sonnet outperforms competitors by up to 4.6 percentage points, achieving 85.0% accuracy. For proprietary models, we observed a universal reduction in cost every 3-to-12 months to achieve similar score in this particular astronomy benchmark. open-weights models have rapidly improved, with LLaMA-3-70b (80.6%) and Qwen-2-72b (77.7%) now competing with some of the best proprietary models. We identify performance variations across topics, with non-English-focused models generally struggling more in exoplanet-related fields, stellar astrophysics, and instrumentation related questions. These challenges likely stem from less abundant training data, limited historical context, and rapid recent developments in these areas. This pattern is observed across both open-weights and proprietary models, with regional dependencies evident, highlighting the impact of training data diversity on model performance in specialized scientific domains. Top-performing models demonstrate well-calibrated confidence, with correlations above 0.9 between confidence and correctness, though they tend to be slightly underconfident. The development for fast, low-cost inference of open-weights models presents new opportunities for affordable deployment in astronomy. The rapid progress observed suggests that LLM-driven research in astronomy may become feasible in the near future.

astro-ph.IM↗

arXiv2024

'Quis custodiet ipsos custodes?' Who will watch the watchmen? On Detecting AI-generated peer-reviews

The integrity of the peer-review process is vital for maintaining scientific rigor and trust within the academic community. With the steady increase in the usage of large language models (LLMs) like ChatGPT in academic writing, there is a growing concern that AI-generated texts could compromise scientific publishing, including peer-reviews. Previous works have focused on generic AI-generated text detection or have presented an approach for estimating the fraction of peer-reviews that can be AI-generated. Our focus here is to solve a real-world problem by assisting the editor or chair in determining whether a review is written by ChatGPT or not. To address this, we introduce the Term Frequency (TF) model, which posits that AI often repeats tokens, and the Review Regeneration (RR) model, which is based on the idea that ChatGPT generates similar outputs upon re-prompting. We stress test these detectors against token attack and paraphrasing. Finally, we propose an effective defensive strategy to reduce the effect of paraphrasing on our models. Our findings suggest both our proposed methods perform better than the other AI text detectors. Our RR model is more robust, although our TF model performs better than the RR model without any attacks. We make our code, dataset, and model public.

cs.CL↗

arXiv2024

AstroMLab 2: AstroLLaMA-2-70B Model and Benchmarking Specialised LLMs for Astronomy

Continual pretraining of large language models on domain-specific data has been proposed to enhance performance on downstream tasks. In astronomy, the previous absence of astronomy-focused benchmarks has hindered objective evaluation of these specialized LLM models. Leveraging a recent initiative to curate high-quality astronomical MCQs, this study aims to quantitatively assess specialized LLMs in astronomy. We find that the previously released AstroLLaMA series, based on LLaMA-2-7B, underperforms compared to the base model. We demonstrate that this performance degradation can be partially mitigated by utilizing high-quality data for continual pretraining, such as summarized text from arXiv. Despite the observed catastrophic forgetting in smaller models, our results indicate that continual pretraining on the 70B model can yield significant improvements. However, the current supervised fine-tuning dataset still constrains the performance of instruct models. In conjunction with this study, we introduce a new set of models, AstroLLaMA-3-8B and AstroLLaMA-2-70B, building upon the previous AstroLLaMA series.

astro-ph.IM↗

arXiv2024

pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy

The exponential growth of astronomical literature poses significant challenges for researchers navigating and synthesizing general insights or even domain-specific knowledge. We present Pathfinder, a machine learning framework designed to enable literature review and knowledge discovery in astronomy, focusing on semantic searching with natural language instead of syntactic searches with keywords. Utilizing state-of-the-art large language models (LLMs) and a corpus of 350,000 peer-reviewed papers from the Astrophysics Data System (ADS), Pathfinder offers an innovative approach to scientific inquiry and literature exploration. Our framework couples advanced retrieval techniques with LLM-based synthesis to search astronomical literature by semantic context as a complement to currently existing methods that use keywords or citation graphs. It addresses complexities of jargon, named entities, and temporal aspects through time-based and citation-based weighting schemes. We demonstrate the tool's versatility through case studies, showcasing its application in various research scenarios. The system's performance is evaluated using custom benchmarks, including single-paper and multi-paper tasks. Beyond literature review, Pathfinder offers unique capabilities for reformatting answers in ways that are accessible to various audiences (e.g. in a different language or as simplified text), visualizing research landscapes, and tracking the impact of observatories and methodologies. This tool represents a significant advancement in applying AI to astronomical research, aiding researchers at all career stages in navigating modern astronomy literature.

astro-ph.IM↗

arXiv2023

When Reviewers Lock Horn: Finding Disagreement in Scientific Peer Reviews

To this date, the efficacy of the scientific publishing enterprise fundamentally rests on the strength of the peer review process. The journal editor or the conference chair primarily relies on the expert reviewers' assessment, identify points of agreement and disagreement and try to reach a consensus to make a fair and informed decision on whether to accept or reject a paper. However, with the escalating number of submissions requiring review, especially in top-tier Artificial Intelligence (AI) conferences, the editor/chair, among many other works, invests a significant, sometimes stressful effort to mitigate reviewer disagreements. Here in this work, we introduce a novel task of automatically identifying contradictions among reviewers on a given article. To this end, we introduce ContraSciView, a comprehensive review-pair contradiction dataset on around 8.5k papers (with around 28k review pairs containing nearly 50k review pair comments) from the open review-based ICLR and NeurIPS conferences. We further propose a baseline model that detects contradictory statements from the review pairs. To the best of our knowledge, we make the first attempt to identify disagreements among peer reviewers automatically. We make our dataset and code public for further investigations.

cs.CL↗

arXiv2022

Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection

A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods' capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.

cs.CL↗

arXiv2022

RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification

Exponential growth in digital information outlets and the race to publish has made scientific misinformation more prevalent than ever. However, the task to fact-verify a given scientific claim is not straightforward even for researchers. Scientific claim verification requires in-depth knowledge and great labor from domain experts to substantiate supporting and refuting evidence from credible scientific sources. The SciFact dataset and corresponding task provide a benchmarking leaderboard to the community to develop automatic scientific claim verification systems via extracting and assimilating relevant evidence rationales from source abstracts. In this work, we propose a modular approach that sequentially carries out binary classification for every prediction subtask as in the SciFact leaderboard. Our simple classifier-based approach uses reduced abstract representations to retrieve relevant abstracts. These are further used to train the relevant rationale-selection model. Finally, we carry out two-step stance predictions that first differentiate non-relevant rationales and then identify supporting or refuting rationales for a given claim. Experimentally, our system RerrFact with no fine-tuning, simple design, and a fraction of model parameters fairs competitively on the leaderboard against large-scale, modular, and joint modeling approaches. We make our codebase available at https://github.com/ashishrana160796/RerrFact.

cs.CL↗

arXiv2018

TAP-DLND 1.0 : A Corpus for Document Level Novelty Detection

Detecting novelty of an entire document is an Artificial Intelligence (AI) frontier problem that has widespread NLP applications, such as extractive document summarization, tracking development of news events, predicting impact of scholarly articles, etc. Important though the problem is, we are unaware of any benchmark document level data that correctly addresses the evaluation of automatic novelty detection techniques in a classification framework. To bridge this gap, we present here a resource for benchmarking the techniques for document level novelty detection. We create the resource via event-specific crawling of news documents across several domains in a periodic manner. We release the annotated corpus with necessary statistics and show its use with a developed system for the problem in concern.

cs.CL↗

arXiv2018

An AI aid to the editors. Exploring the possibility of an AI assisted article classification system

This work is a preliminary exploratory study of how we could progress a step towards an AI assisted article classification sys- tem in academia. The proposed system aims to aid the journal editors in their decisions by pinpointing the potential weaknesses or strengths of a submitted manuscript. From a large collection of articles and corresponding author-editor interactions we explore the possible reasons that lead to a paper being not forwarded for review. Our investigation reveals that in most cases either it is be- cause the prospective manuscript is out of scope of the journal or the manuscript does not satisfy the minimum quality requirements to maintain the standard of the journal. We extract several features to quantify the quality of a paper and the degree of in-scope explor- ing keyword search, citation analysis, reputations of authors and affiliations, similarity with respect to accepted papers. With these features we train standard machine learning classifiers to develop a classification system. On a decent set of test data our approach yields promising results across 3 different journals. We believe that our approach is generic and could be adapted to other journals with appropriate adjustments.

cs.DL↗