arXiv subjects

Sachin Kumar

Publications and source records attributed to Sachin Kumar.

At least 37 records · Page 2Linked to original sources

arXiv2026

ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access

We present ClinicalTrialsHub, an interactive search-focused platform that consolidates all data from ClinicalTrials.gov and augments it by automatically extracting and structuring trial-relevant information from PubMed research articles. Our system effectively increases access to structured clinical trial data by 83.8% compared to relying on ClinicalTrials.gov alone, with potential to make access easier for patients, clinicians, researchers, and policymakers, advancing evidence-based medicine. ClinicalTrialsHub uses large language models such as GPT-5.1 and Gemini-3-Pro to enhance accessibility. The platform automatically parses full-text research articles to extract structured trial information, translates user queries into structured database searches, and provides an attributed question-answering system that generates evidence-grounded answers linked to specific source sentences. We demonstrate its utility through a user study involving clinicians, clinical researchers, and PhD students of pharmaceutical sciences and nursing, and a systematic automatic evaluation of its information extraction and question answering capabilities.

cs.CL↗

arXiv2026

A Comparative Empirical Study of Catastrophic Forgetting Mitigation in Sequential Task Adaptation for Continual Natural Language Processing Systems

Neural language models deployed in real-world applications must continually adapt to new tasks and domains without forgetting previously acquired knowledge. This work presents a comparative empirical study of catastrophic forgetting mitigation in continual intent classification. Using the CLINC150 dataset, we construct a 10-task label-disjoint scenario and evaluate three backbone architectures: a feed-forward Artificial Neural Network (ANN), a Gated Recurrent Unit (GRU), and a Transformer encoder, under a range of continual learning (CL) strategies. We consider one representative method from each major CL family: replay-based Maximally Interfered Retrieval (MIR), regularization-based Learning without Forgetting (LwF), and parameter-isolation via Hard Attention to Task (HAT), both individually and in all pairwise and triple combinations. Performance is assessed with average accuracy, macro F1, and backward transfer, capturing the stability-plasticity trade-off across the task sequence. Our results show that naive sequential fine-tuning suffers from severe forgetting for all architectures and that no single CL method fully prevents it. Replay emerges as a key ingredient: MIR is the most reliable individual strategy, and combinations that include replay (MIR+HAT, MIR+LwF, MIR+LwF+HAT) consistently achieve high final performance with near-zero or mildly positive backward transfer. The optimal configuration is architecture-dependent. MIR+HAT yields the best result for ANN and Transformer, MIR+LwF+HAT, on the other hand, works the best for GRU, and in several cases CL methods even surpass joint training, indicating a regularization effect. These findings highlight the importance of jointly selecting backbone architecture and CL mechanism when designing continual intent-classification systems.

cs.CL↗

arXiv2026

ScholarEval: Research Idea Evaluation Grounded in Literature

As AI tools become increasingly common for research ideation, robust evaluation is critical to ensure the validity and usefulness of generated ideas. We introduce ScholarEval, a retrieval augmented evaluation framework that assesses research ideas based on two fundamental criteria: soundness - the empirical validity of proposed methods based on existing literature, and contribution - the degree of advancement made by the idea across different dimensions relative to prior research. To evaluate ScholarEval, we introduce ScholarIdeas, the first expert-annotated dataset of multi-domain research ideas and reviews, comprised of 117 ideas across four disciplines: artificial intelligence, neuroscience, biochemistry, and ecology. Our evaluation shows that ScholarEval achieves significantly higher coverage of points mentioned in the human expert annotated rubrics in ScholarIdeas compared to all baselines. Furthermore, ScholarEval is consistently preferred over our strongest baseline o4-mini-deep-research, a reasoning and search-enabled agentic system by OpenAI, in terms of evaluation actionability, depth, and evidence support. Our large-scale user study also shows that ScholarEval significantly outperforms deep research in literature engagement, idea refinement, and usefulness. We openly release our code, dataset, and ScholarEval tool for the community to use and build on.

cs.AI↗

arXiv2026

Linguistic Indicators of Early Cognitive Decline in the DementiaBank Pitt Corpus: A Statistical and Machine Learning Study

Background: Subtle changes in spontaneous language production are among the earliest indicators of cognitive decline. Identifying linguistically interpretable markers of dementia can support transparent and clinically grounded screening approaches. Methods: This study analyzes spontaneous speech transcripts from the DementiaBank Pitt Corpus using three linguistic representations: raw cleaned text, a part-of-speech (POS)-enhanced representation combining lexical and grammatical information, and a POS-only syntactic representation. Logistic regression and random forest models were evaluated under two protocols: transcript-level train-test splits and subject-level five-fold cross-validation to prevent speaker overlap. Model interpretability was examined using global feature importance, and statistical validation was conducted using Mann-Whitney U tests with Cliff's delta effect sizes. Results: Across representations, models achieved stable performance, with syntactic and grammatical features retaining strong discriminative power even in the absence of lexical content. Subject-level evaluation yielded more conservative but consistent results, particularly for POS-enhanced and POS-only representations. Statistical analysis revealed significant group differences in functional word usage, lexical diversity, sentence structure, and discourse coherence, aligning closely with machine learning feature importance findings. Conclusion: The results demonstrate that abstract linguistic features capture robust markers of early cognitive decline under clinically realistic evaluation. By combining interpretable machine learning with non-parametric statistical validation, this study supports the use of linguistically grounded features for transparent and reliable language-based cognitive screening.

cs.CL↗

arXiv2026

BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning

Music understanding is a complex task that often requires reasoning over both structural and semantic elements of audio. We introduce BASS, designed to evaluate music understanding and reasoning in audio language models across four broad categories: structural segmentation, lyric transcription, musicological analysis, and artist collaboration. BASS comprises 2658 questions spanning 12 tasks, 1993 unique songs and covering over 138 hours of music from a wide range of genres and tracks, crafted to assess musicological knowledge and reasoning in real-world scenarios. We evaluate 14 open-source and frontier multimodal LMs, finding that even state-of-the-art models struggle on higher-level reasoning tasks such as structural segmentation and artist collaboration, while performing best on lyric transcription. Our analysis reveals that current models leverage linguistic priors effectively but remain limited in reasoning over musical structure, vocal, and musicological attributes. BASS provides an evaluation framework with widespread applications in music recommendation and search and has the potential to guide the development of audio LMs.

cs.SD↗

arXiv2026

Accepted with Minor Revisions: Value of AI-Assisted Scientific Writing

Large Language Models have seen expanding application across domains, yet their effectiveness as assistive tools for scientific writing - an endeavor requiring precision, multimodal synthesis, and domain expertise - remains insufficiently understood. We examine the potential of LLMs to support domain experts in scientific writing, with a focus on abstract composition. We design an incentivized randomized controlled trial with a hypothetical conference setup where participants with relevant expertise are split into an author and reviewer pool. Inspired by methods in behavioral science, our novel incentive structure encourages authors to edit the provided abstracts to an acceptable quality for a peer-reviewed submission. Our 2 x 2 between-subject design expands into two dimensions: the implicit source of the provided abstract and the disclosure of it. We find authors make most edits when editing human-written abstracts compared to AI-generated abstracts without source attribution, often guided by higher perceived readability in AI generation. Upon disclosure of source information, the volume of edits converges in both source treatments. Reviewer decisions remain unaffected by the source of the abstract, but bear a significant correlation with the number of edits made. Careful stylistic edits, especially in the case of AI-generated abstracts, in the presence of source information, improve the chance of acceptance. We find that AI-generated abstracts hold potential to reach comparable levels of acceptability to human-written ones with minimal revision, and that perceptions of AI authorship, rather than objective quality, drive much of the observed editing behavior. Our findings reverberate the significance of source disclosure in collaborative scientific writing.

cs.HC↗

arXiv2026

Fine-Grained Emotion Detection on GoEmotions: Experimental Comparison of Classical Machine Learning, BiLSTM, and Transformer Models

Fine-grained emotion recognition is a challenging multi-label NLP task due to label overlap and class imbalance. In this work, we benchmark three modeling families on the GoEmotions dataset: a TF-IDF-based logistic regression system trained with binary relevance, a BiLSTM with attention, and a BERT model fine-tuned for multi-label classification. Experiments follow the official train/validation/test split, and imbalance is mitigated using inverse-frequency class weights. Across several metrics, namely Micro-F1, Macro-F1, Hamming Loss, and Subset Accuracy, we observe that logistic regression attains the highest Micro-F1 of 0.51, while BERT achieves the best overall balance surpassing the official paper's reported results, reaching Macro-F1 0.49, Hamming Loss 0.036, and Subset Accuracy 0.36. This suggests that frequent emotions often rely on surface lexical cues, whereas contextual representations improve performance on rarer emotions and more ambiguous examples.

cs.CL↗

arXiv2026

GEGO: A Hybrid Golden Eagle and Genetic Optimization Algorithm for Efficient Hyperparameter Tuning in Resource-Constrained Environments

Hyperparameter tuning is a critical yet computationally expensive step in training neural networks, particularly when the search space is high dimensional and nonconvex. Metaheuristic optimization algorithms are often used for this purpose due to their derivative free nature and robustness against local optima. In this work, we propose Golden Eagle Genetic Optimization (GEGO), a hybrid metaheuristic that integrates the population movement strategy of Golden Eagle Optimization with the genetic operators of selection, crossover, and mutation. The main novelty of GEGO lies in embedding genetic operators directly into the iterative search process of GEO, rather than applying them as a separate evolutionary stage. This design improves population diversity during search and reduces premature convergence while preserving the exploration behavior of GEO. GEGO is evaluated on standard unimodal, multimodal, and composite benchmark functions from the CEC2017 suite, where it consistently outperforms its constituent algorithms and several classical metaheuristics in terms of solution quality and robustness. The algorithm is further applied to hyperparameter tuning of artificial neural networks on the MNIST dataset, where GEGO achieves improved classification accuracy and more stable convergence compared to GEO and GA. These results indicate that GEGO provides a balanced exploration-exploitation tradeoff and is well suited for hyperparameter optimization under constrained computational settings.

cs.NE↗

arXiv2025

DRIP: Dynamic patch Reduction via Interpretable Pooling

Recently, the advances in vision-language models, including contrastive pretraining and instruction tuning, have greatly pushed the frontier of multimodal AI. However, owing to the large-scale and hence expensive pretraining, the efficiency concern has discouraged researchers from attempting to pretrain a vision language model from scratch. In this work, we propose Dynamic patch Reduction via Interpretable Pooling (DRIP), which adapts to the input images and dynamically merges tokens in the deeper layers of a visual encoder. Our results on both ImageNet training from scratch and CLIP contrastive pretraining demonstrate a significant GFLOP reduction while maintaining comparable classification/zero-shot performance. To further validate our proposed method, we conduct continual pretraining on a large biology dataset, extending its impact into scientific domains.

cs.CV↗

arXiv2025

CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders

Sparse autoencoders (SAEs) are a promising approach for uncovering interpretable features in large language models (LLMs). While several automated evaluation methods exist for SAEs, most rely on external LLMs. In this work, we introduce CE-Bench, a novel and lightweight contrastive evaluation benchmark for sparse autoencoders, built on a curated dataset of contrastive story pairs. We conduct comprehensive evaluation studies to validate the effectiveness of our approach. Our results show that CE-Bench reliably measures the interpretability of sparse autoencoders and aligns well with existing benchmarks without requiring an external LLM judge, achieving over 70% Spearman correlation with results in SAEBench. The official implementation and evaluation dataset are open-sourced and publicly available.

cs.CL↗

arXiv2025

Continually Adding New Languages to Multilingual Language Models

Multilingual language models are trained on a fixed set of languages, and to support new languages, the models need to be retrained from scratch. This is an expensive endeavor and is often infeasible, as model developers tend not to release their pre-training data. Naive approaches, such as continued pretraining, suffer from catastrophic forgetting; however, mitigation strategies like experience replay cannot be applied due to the lack of original pretraining data. In this work, we investigate the problem of continually adding new languages to a multilingual model, assuming access to pretraining data in only the target languages. We explore multiple approaches to address this problem and propose Layer-Selective LoRA (LayRA), which adds Low-Rank Adapters (LoRA) to selected initial and final layers while keeping the rest of the model frozen. LayRA builds on two insights: (1) LoRA reduces forgetting, and (2) multilingual models encode inputs in the source language in the initial layers, reason in English in intermediate layers, and translate back to the source language in final layers. We experiment with adding multiple combinations of Galician, Swahili, and Urdu to pretrained language models and evaluate each method on diverse multilingual tasks. We find that LayRA provides the overall best tradeoff between preserving models' capabilities in previously supported languages, while being competitive with existing approaches such as LoRA in learning new languages. We also demonstrate that using model arithmetic, the adapted models can be equipped with strong instruction following abilities without access to any instruction tuning data in the target languages.

cs.CL↗

arXiv2025

First-principles investigation of Sr-Ce-M-O perovskites for solar thermochemical water splitting

Using density functional theory based calculations, we systematically examine the utility of Sr-M-O and Sr-Ce-M-O perovskites for solar thermochemical water splitting, a promising route for sustainable hydrogen production. Importantly, we identify Sr$_{0.5}$Ce$_{0.5}$MnO$_3$ and Sr$_{0.5}$Ce$_{0.5}$CrO$_3$ to be promising candidates, exhibiting optimal oxygen vacancy formation energy and 0 K thermodynamic stability.

cond-mat.mtrl-sci↗

arXiv2025

Gaussian pseudo-Orthogonal Ensemble of Real Random Matrices

Here, using two real non-zero parameters $λ$ and $μ$, we construct Gaussian pseudo-orthogonal ensembles of a large number $N$ of $n \times n$ ($n$ even and large) real pseudo-symmetric matrices under the metric $η$ using $ \altmathcal {N}=n(n+1)/2$ elements independently drawn from a Gaussian random population and investigate the statistical properties of the eigenvalues. When $λμ>0$, we show that the pseudo-symmetric matrix is similar to a real symmetric matrix, consequently, all the eigenvalues are real and so the spectral distributions satisfy Wigner's statistics. But when $λμ<0$ the eigenvalues are either real or complex conjugate pairs. We find that these real eigenvalues exhibit intermediate statistics. We show that the diagonalizing matrices ${ \cal D}$ of these pseudo-symmetric matrices are pseudo-orthogonal under a constant metric $ζ$ as $ \altmathcal{D}^t ζ\altmathcal{D}= ζ$, and hence they belong to a pseudo-orthogonal group. These pseudo-symmetric matrices serve to represent the parity-time (PT)-symmetric quantum systems having exact (un-broken) or broken PT-symmetry.

quant-ph↗

arXiv2025

TESS 2: A Large-Scale Generalist Diffusion Language Model

We introduce TESS 2, a general instruction-following diffusion language model that outperforms contemporary instruction-tuned diffusion models, as well as matches and sometimes exceeds strong autoregressive (AR) models. We train TESS 2 by first adapting a strong AR model via continued pretraining with the usual cross-entropy as diffusion loss, and then performing further instruction tuning. We find that adaptation training as well as the choice of the base model is crucial for training good instruction-following diffusion models. We further propose reward guidance, a novel and modular inference-time guidance procedure to align model outputs without needing to train the underlying model. Finally, we show that TESS 2 further improves with increased inference-time compute, highlighting the utility of diffusion LMs in having fine-grained controllability over the amount of compute used at inference time. Code and models are available at https://github.com/hamishivi/tess-2.

cs.CL↗

arXiv2025

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative is to distill preferences from LMs as a source of synthetic annotations, offering a cost-effective and scalable alternative, albeit susceptible to other biases and errors. In this work, we introduce HyPER, a Hybrid Preference routER that defers an annotation to either humans or LMs, achieving better annotation quality while reducing the cost of human-only annotation. We formulate this as an optimization problem: given a preference dataset and an evaluation metric, we (1) train a performance prediction model (PPM) to predict a reward model's (RM) performance on an arbitrary combination of human and LM annotations and (2) employ a routing strategy that selects a combination that maximizes the predicted performance. We train the PPM on MultiPref, a new preference dataset with 10k instances paired with humans and LM labels. We show that the selected hybrid mixture of synthetic and direct human preferences using HyPER achieves better RM performance compared to using either one exclusively by 7-13% on RewardBench and generalizes across unseen preference datasets and other base models. We also observe the same trend in other benchmarks using Best-of-N reranking, where the hybrid mix has 2-3% better performance. Finally, we analyze features from HyPER and find that prompts with moderate safety concerns or complexity benefit the most from human feedback.

cs.CL↗

arXiv2025

BLAB: Brutally Long Audio Bench

Developing large audio language models (LMs) capable of understanding diverse spoken interactions is essential for accommodating the multimodal nature of human communication and can increase the accessibility of language technologies across different user populations. Recent work on audio LMs has primarily evaluated their performance on short audio segments, typically under 30 seconds, with limited exploration of long-form conversational speech segments that more closely reflect natural user interactions with these models. We introduce Brutally Long Audio Bench (BLAB), a challenging long-form audio benchmark that evaluates audio LMs on localization, duration estimation, emotion, and counting tasks using audio segments averaging 51 minutes in length. BLAB consists of 833+ hours of diverse, full-length audio clips, each paired with human-annotated, text-based natural language questions and answers. Our audio data were collected from permissively licensed sources and underwent a human-assisted filtering process to ensure task compliance. We evaluate six open-source and proprietary audio LMs on BLAB and find that all of them, including advanced models such as Gemini 2.0 Pro and GPT-4o, struggle with the tasks in BLAB. Our comprehensive analysis reveals key insights into the trade-offs between task difficulty and audio duration. In general, we find that audio LMs struggle with long-form speech, with performance declining as duration increases. They perform poorly on localization, temporal reasoning, counting, and struggle to understand non-phonemic information, relying more on prompts than audio content. BLAB serves as a challenging evaluation framework to develop audio LMs with robust long-form audio understanding capabilities.

cs.AI↗

arXiv2025

Automated Testing of COBOL to Java Transformation

Recent advances in Large Language Model (LLM) based Generative AI techniques have made it feasible to translate enterprise-level code from legacy languages such as COBOL to modern languages such as Java or Python. While the results of LLM-based automatic transformation are encouraging, the resulting code cannot be trusted to correctly translate the original code, making manual validation of translated Java code from COBOL a necessary but time-consuming and labor-intensive process. In this paper, we share our experience of developing a testing framework for IBM Watsonx Code Assistant for Z (WCA4Z) [5], an industrial tool designed for COBOL to Java translation. The framework automates the process of testing the functional equivalence of the translated Java code against the original COBOL programs in an industry context. Our framework uses symbolic execution to generate unit tests for COBOL, mocking external calls and transforming them into JUnit tests to validate semantic equivalence with translated Java. The results not only help identify and repair any detected discrepancies but also provide feedback to improve the AI model.

cs.SE↗

arXiv2025

Automated Validation of COBOL to Java Transformation

Recent advances in Large Language Model (LLM) based Generative AI techniques have made it feasible to translate enterpriselevel code from legacy languages such as COBOL to modern languages such as Java or Python. While the results of LLM-based automatic transformation are encouraging, the resulting code cannot be trusted to correctly translate the original code. We propose a framework and a tool to help validate the equivalence of COBOL and translated Java. The results can also help repair the code if there are some issues and provide feedback to the AI model to improve. We have developed a symbolic-execution-based test generation to automatically generate unit tests for the source COBOL programs which also mocks the external resource calls. We generate equivalent JUnit test cases with equivalent mocking as COBOL and run them to check semantic equivalence between original and translated programs.

cs.SE↗