arXiv subjects

Deepa Tilwani

Publications and source records attributed to Deepa Tilwani.

6 recordsLinked to original sources

arXiv2026

NeuroSymbolic AI for Legal AI-TRISM: Trustworthy, Reliable, Interpretable, Safe Models

Large Language Models (LLMs) have transformed natural language processing, but their lack of interpretable reasoning and tendency to hallucinate pose significant challenges for legal applications. While LLMs show promise for legal text analysis and generation, they struggle with accurate citation attribution and precedent verification. For example, in legal contexts, a single incorrect precedent can jeopardize a case. Current approaches to improve LLM reliability in legal domains suffer from two key limitations: inadequate integration of structured legal knowledge during training or fine-tuning, and insufficient verification mechanisms for generated legal content. To address these challenges, we propose the TRISM (Trustworthy, Reliable, Interpretable, Safe Models) framework, which integrates NeuroSymbolic AI principles with LLMs to leverage both neural learning capabilities and symbolic reasoning over structured legal knowledge. The TRISM approach addresses the above limitations while maintaining interpretable decision pathways. Our framework formalizes the extraction of symbolic knowledge from legal textual documents and incorporates Retrieval-Augmented Generation (RAG) as a core component for grounding LLM outputs in verified legal sources. In this position paper, we make the following contributions: (1) An analysis of the limitations of AI in law; (2) Introduce RASOR RAG which creates foundations for neurosymbolic RAG by generating explicit interpretable rationales that could be formalized into symbolic representations; (3) A formalized methodology for creating symbolic legal knowledge bases that support both interpretable reasoning and output verification in LLMs; and (4) The TRISM framework for integrating symbolic legal knowledge with LLMs.

cs.AI↗

arXiv2024

Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation

Malware authors often employ code obfuscations to make their malware harder to detect. Existing tools for generating obfuscated code often require access to the original source code (e.g., C++ or Java), and adding new obfuscations is a non-trivial, labor-intensive process. In this study, we ask the following question: Can Large Language Models (LLMs) potentially generate a new obfuscated assembly code? If so, this poses a risk to anti-virus engines and potentially increases the flexibility of attackers to create new obfuscation patterns. We answer this in the affirmative by developing the MetamorphASM benchmark comprising MetamorphASM Dataset (MAD) along with three code obfuscation techniques: dead code, register substitution, and control flow change. The MetamorphASM systematically evaluates the ability of LLMs to generate and analyze obfuscated code using MAD, which contains 328,200 obfuscated assembly code samples. We release this dataset and analyze the success rate of various LLMs (e.g., GPT-3.5/4, GPT-4o-mini, Starcoder, CodeGemma, CodeLlama, CodeT5, and LLaMA 3.1) in generating obfuscated assembly code. The evaluation was performed using established information-theoretic metrics and manual human review to ensure correctness and provide the foundation for researchers to study and develop remediations to this risk.

cs.CR↗

arXiv2024

Neurosymbolic AI approach to Attribution in Large Language Models

Attribution in large language models (LLMs) remains a significant challenge, particularly in ensuring the factual accuracy and reliability of the generated outputs. Current methods for citation or attribution, such as those employed by tools like Perplexity.ai and Bing Search-integrated LLMs, attempt to ground responses by providing real-time search results and citations. However, so far, these approaches suffer from issues such as hallucinations, biases, surface-level relevance matching, and the complexity of managing vast, unfiltered knowledge sources. While tools like Perplexity.ai dynamically integrate web-based information and citations, they often rely on inconsistent sources such as blog posts or unreliable sources, which limits their overall reliability. We present that these challenges can be mitigated by integrating Neurosymbolic AI (NesyAI), which combines the strengths of neural networks with structured symbolic reasoning. NesyAI offers transparent, interpretable, and dynamic reasoning processes, addressing the limitations of current attribution methods by incorporating structured symbolic knowledge with flexible, neural-based learning. This paper explores how NesyAI frameworks can enhance existing attribution models, offering more reliable, interpretable, and adaptable systems for LLMs.

cs.CL↗

arXiv2024

Deep Jansen-Rit Parameter Inference for Model-Driven Analysis of Brain Activity

Accurately modeling effective connectivity (EC) is critical for understanding how the brain processes and integrates sensory information. Yet, it remains a formidable challenge due to complex neural dynamics and noisy measurements such as those obtained from the electroencephalogram (EEG). Model-driven EC infers local (within a brain region) and global (between brain regions) EC parameters by fitting a generative model of neural activity onto experimental data. This approach offers a promising route for various applications, including investigating neurodevelopmental disorders. However, current approaches fail to scale to whole-brain analyses and are highly noise-sensitive. In this work, we employ three deep-learning architectures--a transformer, a long short-term memory (LSTM) network, and a convolutional neural network and bidirectional LSTM (CNN-BiLSTM) network--for inverse modeling and compare their performance with simulation-based inference in estimating the Jansen-Rit neural mass model (JR-NMM) parameters from simulated EEG data under various noise conditions. We demonstrate a reliable estimation of key local parameters, such as synaptic gains and time constants. However, other parameters like local JR-NMM connectivity cannot be evaluated reliably from evoked-related potentials (ERP). We also conduct a sensitivity analysis to characterize the influence of JR-NMM parameters on ERP and evaluate their learnability. Our results show the feasibility of deep-learning approaches to estimate the subset of learnable JR-NMM parameters.

q-bio.NC↗

arXiv2024

Attribution in Scientific Literature: New Benchmark and Methods

Large language models (LLMs) increasingly generate citation-backed responses, yet citation hallucination remains a major challenge for trustworthy scientific information access. We introduce REASONS, a benchmark of 12,723 sentence-level citation instances spanning 12 arXiv subject categories, designed to evaluate scientific citation attribution under varying evidence conditions. We propose a dual-metric framework consisting of Abstention Rate (AR) and Hallucination Rate (HR) to characterize the trade-off between reliability and responsiveness. Using author-attribution and title-attribution tasks, we evaluate proprietary and open-source LLMs under zero-context, metadata-augmented, cascaded metadata-augmented prompting (CMP), retrieval-augmented, and adversarial settings. Advanced RAG lowers HR relative to Naive RAG (65.4% vs. 87.6%) but reduces AR from 5.0% to 0%. Under adversarial metadata, several systems exceed 85% HR, while retrieval-augmented variants frequently maintain near-zero abstention. Human evaluation of 1,000 outputs ($\kappa=0.78$) finds a 12.7:1 ratio of factual hallucinations to acceptable paraphrases. Our findings demonstrate that citation attribution systems should be evaluated not only for correctness but also for their ability to abstain appropriately under uncertainty. REASONS provides a benchmark and evaluation framework for studying attribution reliability in citation generation.

cs.CL↗

arXiv2023

A Cross Attention Approach to Diagnostic Explainability using Clinical Practice Guidelines for Depression

The lack of explainability using relevant clinical knowledge hinders the adoption of Artificial Intelligence-powered analysis of unstructured clinical dialogue. A wealth of relevant, untapped Mental Health (MH) data is available in online communities, providing the opportunity to address the explainability problem with substantial potential impact as a screening tool for both online and offline applications. We develop a method to enhance attention in popular transformer models and generate clinician-understandable explanations for classification by incorporating external clinical knowledge. Inspired by how clinicians rely on their expertise when interacting with patients, we leverage relevant clinical knowledge to model patient inputs, providing meaningful explanations for classification. This will save manual review time and engender trust. We develop such a system in the context of MH using clinical practice guidelines (CPG) for diagnosing depression, a mental health disorder of global concern. We propose an application-specific language model called ProcesS knowledge-infused cross ATtention (PSAT), which incorporates CPGs when computing attention. Through rigorous evaluation on three expert-curated datasets related to depression, we demonstrate application-relevant explainability of PSAT. PSAT also surpasses the performance of nine baseline models and can provide explanations where other baselines fall short. We transform a CPG resource focused on depression, such as the Patient Health Questionnaire (e.g. PHQ-9) and related questions, into a machine-readable ontology using SNOMED-CT. With this resource, PSAT enhances the ability of models like GPT-3.5 to generate application-relevant explanations.

cs.AI↗