arXiv subjects

Sanchit Kabra

Publications and source records attributed to Sanchit Kabra.

10 recordsLinked to original sources

arXiv2026

LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search

Recovering governing Ordinary Differential Equations (ODEs) from data is a central challenge in modeling dynamical systems across scientific domains. Existing approaches cast discovery as a static inference problem over fixed datasets, assuming that the observed trajectories are sufficiently informative. However, dynamical systems evolve over large state spaces, and limited data can make multiple equations observationally indistinguishable, leading to identifiability gaps and the recovery of incorrect governing equations. To address this, we introduce LLM-ACES, or LLM-guided Active Closed-loop Equation Search, a closed-loop framework that jointly optimizes symbolic hypothesis construction and adaptive data acquisition. In LLM-ACES, a large language model (LLM) proposes operator priors that partition the large search space into distinct regions, within which candidate equations are fit to the observed data. The disagreement among these candidates guides the acquisition of informative trajectories, creating a feedback loop that iteratively refines both the hypothesis space and the discovered dynamics. On 122 ODE systems spanning ODEBench and ODEBase, LLM-ACES achieves the lowest median NMSE, outperforming state-of-the-art baselines by several orders of magnitude while achieving a high symbolic accuracy of 46.2% and 52.4%, respectively. Our analysis further shows that LLM-ACES is sample-efficient, achieving better performance with one-tenth the data. Furthermore, LLM-ACES's feedback-driven data acquisition makes it robust to noise and recovers the correct symbolic structure, while baselines introduce spurious terms that fit the data locally but obscure the true governing relationships.

cs.LG↗

arXiv2026

LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs

Scientific discovery is a closed-loop process in which hypotheses guide data acquisition and observations refine the hypothesis space. Yet most approaches reduce discovery to supervised learning over fixed datasets, where limited observations can support multiple plausible mechanisms that fit locally but fail to generalize. Thus, the key challenge is selecting informative observations to resolve uncertainty, shifting the focus from static inference to adaptive data acquisition. To address this, we propose LLM-AutoSciLab, a closed-loop framework that couples hypothesis generation with hypothesis-conditioned experiment selection and mechanism refinement. Rather than fitting models to passively collected data, LLM-AutoSciLab iteratively proposes plausible hypotheses, selects informative experiments to distinguish or refine them, and updates its state using the resulting evidence. To evaluate dynamic, closed-loop scientific discovery with active data acquisition, we introduce ActiveSciBench, comprising two datasets: ActiveSciBench-Chem with 57 enzyme-kinetics tasks and ActiveSciBench-GRN with 45 gene-regulatory-network tasks. These datasets model discovery as a budget-constrained process requiring adaptive experiment design, variable selection, and recovery of true mechanisms. Across NewtonBench, ActiveSciBench-Chem, and ActiveSciBench-GRN, LLM-AutoSciLab outperforms prior methods, achieving 67.6% and 35.1% symbolic accuracy on NewtonBench and ActiveSciBench-Chem, respectively, and 31.1% exact graph recovery on ActiveSciBench-GRN. Moreover, hypothesis-guided experimentation is 2-5x more sample-efficient than the strongest competing baselines. Code and data are available at: https://github.com/scientific-discovery/LLM-AutoSciLab

cs.LG↗

arXiv2026

LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery

Materials discovery requires navigating vast chemical and structural spaces while satisfying multiple, often conflicting, objectives. We present LLM-guided Evolution for MAterials discovery (LLEMA), a unified framework that couples the scientific knowledge embedded in large language models with chemistry-informed evolutionary rules and memory-based refinement. At each iteration, an LLM proposes crystallographically specified candidates under explicit property constraints; a surrogate-augmented oracle estimates physicochemical properties; and a multi-objective scorer updates success/failure memories to guide subsequent generations. Evaluated on 14 realistic tasks that span electronics, energy, coatings, optics, and aerospace, LLEMA discovers candidates that are chemically plausible, thermodynamically stable, and property-aligned, achieving higher hit rates and improved Pareto front quality relative to generative and LLM-only baselines. Ablation studies confirm the importance of rule-guided generation, memory-based refinement, and surrogate prediction. By enforcing synthesizability and multi-objective trade-offs, LLEMA provides a principled approach to accelerating practical materials discovery. Project website: https://scientific-discovery.github.io/llema-project/

cs.LG↗

arXiv2026

SURFACEBENCH: A Geometry-Aware Benchmark for Symbolic Surface Discovery

Equation discovery from data is a central challenge in machine learning for science, which requires the recovery of concise symbolic expressions that govern complex physical and geometric phenomena. Recent large language model (LLM) approaches have shown promise in symbolic regression, yet existing benchmarks predominantly evaluate low-dimensional scalar functions and rely on string-level or regression-based metrics that fail to capture structural and geometric equivalence. We introduce SURFACEBENCH, the first geometry-aware benchmark for symbolic discovery of three-dimensional surfaces. Unlike scalar curve-fitting tasks, SURFACEBENCH targets surface-level reasoning, where multi-variable coupling, coordinate transformations, and geometric structure must be inferred directly from data. The benchmark comprises 183 analytically constructed, science-inspired surface equations across 15 categories and three representation paradigms: explicit, implicit, and parametric forms. Each task includes variable semantics and synthetically sampled 3D data, and is designed to stress symbolic composition, structural ambiguity, and representational non-uniqueness while mitigating memorization. To evaluate discovery quality, SURFACEBENCH incorporates symbolic equivalence checks with geometric metrics of the object-space (Chamfer and Hausdorff distances) and regression-based error measures, allowing evaluation of functional fidelity beyond algebraic syntax. Empirical evaluation across evolutionary, neural, and LLM-driven frameworks reveals that no current method achieves consistent performance across representation types, with LLM-based approaches exhibiting strong structural priors but limited robustness in parameter calibration and multi-equation reasoning.The code and data are available at this link: github.com/deep-symbolic-mathematics/surfacebench.

cs.LG↗

arXiv2025

Beyond Single Bugs: Benchmarking Large Language Models for Multi-Vulnerability Detection

Large Language Models (LLMs) have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or function-level classification, failing to reflect the complexity of real-world software where multiple interacting vulnerabilities often coexist within large files. Recent studies indicate that LLMs suffer from "count bias" and "selection bias" in multi-label tasks, yet this has not been rigorously quantified in the domain of code security. In this work, we introduce a comprehensive benchmark for Multi-Vulnerability Detection across four major languages: C, C++, Python, and JavaScript. We construct a dataset of 40,000 files by systematically injecting controlled counts of vulnerabilities (1, 3, 5, and 9) into long-context code samples (7.5k-10k tokens) sourced from CodeParrot. We evaluate five state-of-the-art LLMs, including GPT-4o-mini, Llama-3.3-70B, and the Qwen-2.5 series. Our results reveal a sharp degradation in performance as vulnerability density increases. While Llama-3.3-70B achieves near-perfect F1 scores (approximately 0.97) on single-vulnerability C tasks, performance drops by up to 40% in high-density settings. Notably, Python and JavaScript show distinct failure modes compared to C/C++, with models exhibiting severe "under-counting" (Recall dropping to less than 0.30) in complex Python files.

cs.CR↗

arXiv2025

RUST-BENCH: Benchmarking LLM Reasoning on Unstructured Text within Structured Tables

Existing tabular reasoning benchmarks mostly test models on small, uniform tables, underrepresenting the complexity of real-world data and giving an incomplete view of Large Language Models' (LLMs) reasoning abilities. Real tables are long, heterogeneous, and domain-specific, mixing structured fields with free text and requiring multi-hop reasoning across thousands of tokens. To address this gap, we introduce RUST-BENCH, a benchmark of 7966 questions from 2031 real-world tables spanning two domains: i) RB-Science (NSF grant records) and ii) RB-Sports (NBA statistics). Unlike prior work, RUST-BENCH evaluates LLMs jointly across scale, heterogeneity, domain specificity, and reasoning complexity. Experiments with open-source and proprietary models show that LLMs struggle with heterogeneous schemas and complex multi-hop inference, revealing persistent weaknesses in current architectures and prompting strategies. RUST-BENCH establishes a challenging new testbed for advancing tabular reasoning research.

cs.CL↗

arXiv2025

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

Recent advances in large-scale generative language models have shown that reasoning capabilities can significantly improve model performance across a variety of tasks. However, the impact of reasoning on a model's ability to mitigate stereotypical responses remains largely underexplored. In this work, we investigate the crucial relationship between a model's reasoning ability and fairness, and ask whether improved reasoning capabilities can mitigate harmful stereotypical responses, especially those arising due to shallow or flawed reasoning. We conduct a comprehensive evaluation of multiple open-source LLMs, and find that larger models with stronger reasoning abilities exhibit substantially lower stereotypical bias on existing fairness benchmarks. Building on this insight, we introduce ReGiFT -- Reasoning Guided Fine-Tuning, a novel approach that extracts structured reasoning traces from advanced reasoning models and infuses them into models that lack such capabilities. We use only general-purpose reasoning and do not require any fairness-specific supervision for bias mitigation. Notably, we see that models fine-tuned using ReGiFT not only improve fairness relative to their non-reasoning counterparts but also outperform advanced reasoning models on fairness benchmarks. We also analyze how variations in the correctness of the reasoning traces and their length influence model fairness and their overall performance. Our findings highlight that enhancing reasoning capabilities is an effective, fairness-agnostic strategy for mitigating stereotypical bias caused by reasoning flaws.

cs.CL↗

arXiv2025

Aligned at the Start: Conceptual Groupings in LLM Embeddings

This paper shifts focus to the often-overlooked input embeddings - the initial representations fed into transformer blocks. Using fuzzy graph, k-nearest neighbor (k-NN), and community detection, we analyze embeddings from diverse LLMs, finding significant categorical community structure aligned with predefined concepts and categories aligned with humans. We observe these groupings exhibit within-cluster organization (such as hierarchies, topological ordering, etc.), hypothesizing a fundamental structure that precedes contextual processing. To further investigate the conceptual nature of these groupings, we explore cross-model alignments across different LLM categories within their input embeddings, observing a medium to high degree of alignment. Furthermore, provide evidence that manipulating these groupings can play a functional role in mitigating ethnicity bias in LLM tasks.

cs.CL↗

arXiv2024

Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension failure. For example, when a model misinterprets a text and produces a response that reinforces a stereotype, it becomes difficult to determine whether the issue arises from inherent bias or from a misunderstanding of the given content. In this paper, we conduct a multi-faceted evaluation that distinctly disentangles bias from flaws within the reading comprehension task. We propose a targeted stereotype mitigation framework that implicitly mitigates observed stereotypes in generative models through instruction-tuning on general-purpose datasets. We reduce stereotypical outputs by over 60% across multiple dimensions -- including nationality, age, gender, disability, and physical appearance -- by addressing comprehension-based failures, and without relying on explicit debiasing techniques. We evaluate several state-of-the-art generative models to demonstrate the effectiveness of our approach while maintaining the overall utility. Our findings highlight the need to critically disentangle the concept of `bias' from other types of errors to build more targeted and effective mitigation strategies. CONTENT WARNING: Some examples contain offensive stereotypes.

cs.CL↗

arXiv2023

AMaizeD: An End to End Pipeline for Automatic Maize Disease Detection

This research paper presents AMaizeD: An End to End Pipeline for Automatic Maize Disease Detection, an automated framework for early detection of diseases in maize crops using multispectral imagery obtained from drones. A custom hand-collected dataset focusing specifically on maize crops was meticulously gathered by expert researchers and agronomists. The dataset encompasses a diverse range of maize varieties, cultivation practices, and environmental conditions, capturing various stages of maize growth and disease progression. By leveraging multispectral imagery, the framework benefits from improved spectral resolution and increased sensitivity to subtle changes in plant health. The proposed framework employs a combination of convolutional neural networks (CNNs) as feature extractors and segmentation techniques to identify both the maize plants and their associated diseases. Experimental results demonstrate the effectiveness of the framework in detecting a range of maize diseases, including powdery mildew, anthracnose, and leaf blight. The framework achieves state-of-the-art performance on the custom hand-collected dataset and contributes to the field of automated disease detection in agriculture, offering a practical solution for early identification of diseases in maize crops advanced machine learning techniques and deep learning architectures.

cs.CV↗