arXiv subjects

Dhruv Agarwal

Publications and source records attributed to Dhruv Agarwal.

At least 19 recordsLinked to original sources

arXiv2026

Long-term Measurements: Towards a Longitudinal Understanding of Human-AI Interactions

Language models have taken on the role of a very new type of technology, by virtue of their "human-ness" and rapid integration into users' daily lives. This combination of features can introduce longitudinal risks---cognitive, developmental and socio-affective changes in humans---that might not surface during a short-term interaction, but can have lasting long-term effects on users. This forms the basis of a critical new mission for NLP: to pivot from static, short-term evaluations of text generations to long-term measurements of behavioral changes, towards a diachronic understanding of human-model interactions. In this work, we draw from measurements used in social science fields that are crucial to understand emergent phenomena in longitudinal data. We discuss how computational methods in the field of NLP need to be combined with such measurements, not only to understand long-term safety risks of human-model interactions, but to help steer model development towards positive rather than negative outcomes for users. This ability to model human behavioral shifts as a function of model interactions can facilitate online rather than post-hoc detection of problematic behaviors, and should be leveraged in alignment frameworks to mitigate long-term risks in users.

cs.AI↗

arXiv2026

Baikal: Structured Search for Deep Research over Data Lakes

Deep research over data lakes requires an LLM agent to investigate evidence across thousands of heterogeneous tables and passages to synthesize a report. Existing methods perform iterative retrieval and generation, letting accumulated context determine what to investigate next, which can overexploit locally promising evidence and fail to cover distinct semantic regions under a fixed budget. To address this, we cast deep research over data lakes as a budgeted search problem and present Baikal - a framework that clusters heterogeneous evidence into semantic regions, then searches over them adaptively to balance exploration and exploitation. Within each selected region, Baikal generates and investigates region-grounded subquestions, using finding quality as rewards to update region-level value estimates and guide search under policies ranging from random and LLM-guided selection to Bayesian $ε$-greedy and UCB. We evaluate Baikal on 15 queries each over HybridQA and TAT-QA data lakes containing 10,993 and 2,757 tables, respectively, together with 227K Wikipedia passages and 13K financial report passages. We assess research quality with a new rubric covering groundedness, relevance, diversity, and utility, and use GPT-5-mini to score Baikal and strong baselines, including DeepSearcher and an OpenCode research agent with retrieval and clustering variants. Across both data lakes, Baikal performs strongly under several region-selection policies; its best configuration improves report scores over the strongest baselines by 28% on HybridQA and 36% on TAT-QA. Our analyses attribute these gains to organizing and exploring semantic evidence regions, which improves groundedness and diversity and yields more useful findings under the same subquestion budget. These results demonstrate the value of structured semantic exploration for systematic research and discovery over heterogeneous data lakes.

cs.AI↗

arXiv2026

PLURAL: A Global Dataset for Value Alignment

Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nationally representative survey spanning 92 countries. Using a two-stage generation pipeline, we transform survey responses into synthetic preference triplets that preserve normative value signals while producing realistic scenarios. We release an initial version of PLURAL containing ~500,000 preference triplets representing people in 20 diverse countries. We evaluate PLURAL in three ways: (i) dataset-level validation showing that it preserves both cross-country value differences and within-country diversity from the original survey; (ii) automated evaluation showing that training on PLURAL improves alignment with target countries' cultural profiles, reducing mean absolute error by up to 27.7% relative to strong baselines; and (iii) blind human evaluation with 176 evaluators in India, Brazil, and Japan, who judge PLURAL-aligned responses as more representative of their national values. Together, these results show that PLURAL contains learnable signal for value steering, offering a scalable resource for pluralistic alignment. Dataset: https://huggingface.co/datasets/agdhruv/plural-alignment

cs.CL↗

arXiv2026

Evidence-Informed LLM Beliefs for Continual Scientific Discovery

Open-ended scientific discovery with large language models (LLMs) increasingly operates as a long-horizon loop of hypothesis search and verification, where a reward signal guides which hypotheses to test next. A notable recent example is AutoDiscovery, which uses "Bayesian surprise" - the belief shift an LLM undergoes after observing evidence for a hypothesis - as both a discovery metric and a reward for search. We first observe that AutoDiscovery treats surprisal as a static quantity, while surprisal in human reasoning is non-stationary - it is defined relative to beliefs that evolve with experience, a prerequisite for continual scientific discovery. We address this mismatch with evidence-informed LLM beliefs: priors updated with evidence from previous hypotheses to compute non-stationary surprisal for new hypotheses. We compare in-context belief-updating mechanisms and find that embedding-based retrieval-augmented generation over prior discoveries best anticipates eventual posteriors, identifying 37.5% of static surprisals as spurious. We then modify search to avoid these spurious rewards and prioritize hypotheses that remain surprising under non-stationary beliefs. Concretely, we introduce two complementary changes to the original search procedure: belief-update filtering and diversity maximization. Across five discovery domains, our method increases accumulated non-stationary surprisal by 30.62% on average compared to the original search procedure, demonstrating that continual scientific discovery with LLMs requires not only better belief measurement but also search procedures that avoid redundancy and encourage diversity.

cs.AI↗

arXiv2026

The Metric Picks the Winner: Evaluation Choice Flips Model Rankings for Drug-Response Prediction in Unseen Chemistry

Predicting how a cell's transcriptome responds to a drug it has never seen is a core, hard problem in computational cell biology: recent benchmarks show complex models often fail to beat trivial baselines once test compounds are held out by chemistry. We study one cell line and assay, THP-1 cells profiled by DRUG-seq, scored by the active-compound weighted MSE(wMSE) of the VCPI prediction contest. We propose a staged approach: dumb baselines (untreated control and mean training-compound response) that the field keeps failing to beat; non-parametric retrieval (a Tanimoto-weighted average of a held-out compound's nearest training compounds); and a fusion stage combining a frozen chemistry embedding with retrieval-support features to predict the residual over the mean, with an uncertainty head and gene programs. On the released VCPI THP-1 drug-seq data (14,026 training compounds), under a Bemis-Murcko scaffold split, the model ranking inverts depending on the metric. Under an inverse-variance per-gene proxy, a regularized linear regression on Morgan fingerprints appears to win over the deep models, retrieval, and ChemBERTa -- the textbook "simple baselines win" result. But under the contest's true active-set metric (per-(gene, compound) Mejia weights, validated against the official scorer; mean baseline 0.535 vs the organizers' 0.507 reference), that reverses: the deep models win, our fusion decoder significantly beats the linear fingerprint baseline (-0.012 wMSE, paired bootstrap p < 10^-4), and the proxy's winner becomes the worst chemistry-aware predictor. Picking the metric picks the winner -- to our knowledge the first demonstration on real held-out drug chemistry of the metric-calibration effect established largely on genetic perturbation. We release a reproducible pipeline wired to the official scorer that emits a valid submission over the real 1064 x 12,995 grid.

cs.LG↗

arXiv2026

Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter

Machine-learning drug-discovery pipelines increasingly rely on generative models that propose molecules far from the data used to train downstream synthesizability filters. Existing filters (SAScore, SCScore, RAscore, DeepSA) are purely statistical and degrade in exactly this out-of-distribution (OOD) regime. We ask whether cheap, closed-form physical priors, used as auxiliary supervision on a graph neural network (GNN), improve OOD generalization. We add two auxiliary losses to a GINE backbone: a topological complexity regression supervised by the Bertz index, and a strain-energy soft penalty supervised by MMFF94 force-field energy. On a 65,177-molecule corpus (HIV, Tox21, COCONUT) labeled by SAScore thresholds we reproduce a strong in-distribution baseline, then evaluate a 4-way ablation (baseline / +complexity / +strain / +both) on a single-source OOD split (train on drug-like HIV+Tox21, test on COCONUT natural products), repeated over 5 seeds with paired bootstrap confidence intervals. All three physics-aware variants give a small but statistically significant OOD improvement over the baseline (mean OOD AUC 0.9774): +complexity Delta = +0.0060 (95% CI [+0.0023, +0.0102]), +strain Delta = +0.0032 ([+0.0008, +0.0052]), +both Delta = +0.0066 ([+0.0038, +0.0093]); every interval excludes zero, and the combination is best. The variants are indistinguishable in-distribution, so the effect is visible only under OOD evaluation. We are explicit that the effects are modest, and we report a cautionary methodological finding: a single-seed version of this experiment produced a qualitatively different (non-monotone) story that did not survive multi-seed evaluation.

cs.LG↗

arXiv2026

Physics-Informed Neural Networks for Chemotherapy Pharmacokinetics: Benchmarking the Clinical Estimator and Exposing Parameter Identifiability

Physics-Informed Neural Networks (PINNs) are an attractive tool for partial-observation problems in biology, where the governing dynamics are known but some compartments cannot be measured. Chemotherapy pharmacokinetics (PK) is a clean instance: drug concentration in plasma is routinely measured, but concentration in tissue -- which determines tumour kill and off-target toxicity -- is not. We benchmark a PINN against the standard clinical baseline (nonlinear least-squares on the analytical biexponential plasma solution, hereafter NLS) and a physics-agnostic neural baseline (a data-only MLP) on two PK problems. On the linear two-compartment problem, NLS is near-optimal; the PINN matches it to within a small constant factor while also producing the tissue curve in a single training pass, whereas the data-only MLP fails on tissue by roughly 10x. On a Michaelis-Menten extension (saturable elimination), the biexponential closed form no longer exists, so NLS is mis-specified and silently returns meaningless rate constants. The PINN instead exposes a deeper fact: the Michaelis-Menten two-compartment model is non-identifiable from plasma alone, and the PINN reports this honestly by converging to a basin with k12 -> 0. Adding two sparse tissue observations largely resolves identifiability: across five seeds the PINN recovers k21 to within 1% of truth and Vmax, Km to within one standard-deviation bar, while k12 moves in the correct direction (0.02 -> 0.82) but remains ~2 sigma below truth -- a recovery the closed-form NLS estimator cannot attempt at all, because its biexponential ansatz describes only plasma. Our claim is not that PINNs beat NLS. It is that PINNs offer a uniform recipe that ties the textbook estimator on the textbook problem, exposes structural identifiability that the textbook estimator hides, and absorbs heterogeneous measurements within a single loss.

cs.LG↗

arXiv2026

AI-Assisted Systematization for Evaluating GenAI Systems

Evaluating generative AI (GenAI) systems is challenging because many targets of evaluation are broad, contested concepts, such as "reasoning," "fairness," or "creativity." When these concepts are left underspecified, it becomes unclear what should be measured or how evaluation results should be interpreted. This problem reflects a missing step: systematization, that is, moving from a broad background concept to an explicit, structured account of the concept in measurable terms. To help address the fact that systematization is cognitively demanding and resource-intensive, we investigate whether AI assistance can support this process. To enable AI-assisted systematization and assess its quality, we introduce a structured representation of a systematized concept, a concept spec, and a validation worksheet. We then develop two AI-assisted systematizers: a direct, zero-shot approach and a multi-agent approach that more closely mirrors manual systematization approaches from existing literature. We use these systematizers to produce concept specs for two concepts -- hate-based rhetoric and digital empathy -- and evaluate resulting concept specs on content validity and information recoverability.

cs.CL↗

arXiv2026

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

The promise of autonomous scientific discovery (ASD) hinges not only on answering questions, but also on knowing which questions to ask. Most recent works in ASD explore the use of large language models (LLMs) in goal-driven settings, relying on human-specified research questions to guide hypothesis generation. However, scientific discovery may be accelerated further by allowing the AI system to drive exploration by its own criteria. The few existing approaches in open-ended ASD select hypotheses based on diversity heuristics or subjective proxies for human interestingness, but the former struggles to meaningfully navigate the typically vast hypothesis space, and the latter suffers from imprecise definitions. This paper presents AutoDiscovery -- a method for open-ended ASD that instead drives scientific exploration using Bayesian surprise. Here, we quantify the epistemic shift from the LLM's prior beliefs about a hypothesis to its posterior beliefs after gathering experimental results. To efficiently explore the space of nested hypotheses, our method employs a Monte Carlo tree search (MCTS) strategy with progressive widening using surprisal as the reward function. We evaluate AutoDiscovery in the setting of data-driven discovery across 21 real-world datasets spanning domains such as biology, economics, finance, and behavioral science. Our results demonstrate that under a fixed budget, AutoDiscovery substantially outperforms competitors by producing 5-29% more discoveries deemed surprising by the LLM. Our human evaluation further reveals that two-thirds of discoveries made by our system are surprising to domain experts as well, suggesting this is an important step towards building open-ended ASD systems.

cs.LG↗

arXiv2026

Understanding Frechet Speech Distance for Synthetic Speech Quality Evaluation

Objective evaluation of synthetic speech quality remains a critical challenge. Human listening tests are the gold standard, but costly and impractical at scale. Fréchet Distance has emerged as a promising alternative, yet its reliability depends heavily on the choice of embeddings and experimental settings. In this work, we comprehensively evaluate Fréchet Speech Distance (FSD) and its variant Speech Maximum Mean Discrepancy (SMMD) under varied embeddings and conditions. We further incorporate human listening evaluations alongside TTS intelligibility and synthetic-trained ASR WER to validate the perceptual relevance of these metrics. Our findings show that WavLM Base+ features yield the most stable alignment with human ratings. While FSD and SMMD cannot fully replace subjective evaluation, we show that they can serve as complementary, cost-efficient, and reproducible measures, particularly useful when large-scale or direct listening assessments are infeasible. Code is available at https://github.com/kaen2891/FrechetSpeechDistance.

cs.SD↗

arXiv2026

Fluent but Foreign: Even Regional LLMs Lack Cultural Alignment

Large language models (LLMs) are used worldwide, yet exhibit Western cultural tendencies. Many countries are now building ``regional'' or ``sovereign'' LLMs, but it remains unclear whether they reflect local values and practices or merely speak local languages. Using India as a case study, we evaluate six Indic and six global LLMs on two dimensions -- values and practices -- grounded in nationally representative surveys and community-sourced QA datasets. Across tasks, Indic models do not align better with Indian norms than global models; in fact, a U.S. respondent is a closer proxy for Indian values than any Indic model. We further run a user study with 115 Indian users and find that writing suggestions from both global and Indic LLMs introduce Westernized or exoticized writing. Prompting and regional fine-tuning fail to recover alignment and can even degrade existing knowledge. We attribute this to scarce culturally grounded data, especially for pretraining. We position cultural evaluation as a first-class requirement alongside multilingual benchmarks and offer a reusable, community-grounded methodology. We call for native, community-authored corpora and thickxwide evaluations to build truly sovereign LLMs.

cs.CL↗

arXiv2025

Pothole Detection and Analysis System (PoDAS) for Real Time Data Using Sensor Networks

Potholes are a major nuisance on the city roads leading to several problems and losses in productivity. Local authorities have cited a lack of geographic localization of these potholes as one of the rate-limiting factors for repairs. This study proposes a novel low-cost wireless sensor-based end-to-end system called PoDAS (Pothole Detection and Analysis System) which can be deployed across major cities. We discuss multiple implementation models that can be varied based on the needs of individual cities. Our system uses cross-validation through multiple sensors to achieve higher efficiency than some of the previous models that have been proposed. We also present the results from extensive testing carried out in different environments to ascertain both the efficacy and the efficiency of the proposed system.

cs.CY↗

arXiv2025

MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time

Large language models (LLMs) are increasingly being applied to black-box optimization tasks, from program synthesis to molecule design. Prior work typically leverages in-context learning to iteratively guide the model towards better solutions. Such methods, however, often struggle to balance exploration of new solution spaces with exploitation of high-reward ones. Recently, test-time training (TTT) with synthetic data has shown promise in improving solution quality. However, the need for hand-crafted training data tailored to each task limits feasibility and scalability across domains. To address this problem, we introduce MiGrATe-a method for online TTT that uses GRPO as a search algorithm to adapt LLMs at inference without requiring external training data. MiGrATe operates via a mixed-policy group construction procedure that combines on-policy sampling with two off-policy data selection techniques: greedy sampling, which selects top-performing past completions, and neighborhood sampling (NS), which generates completions structurally similar to high-reward ones. Together, these components bias the policy gradient towards exploitation of promising regions in solution space, while preserving exploration through on-policy sampling. We evaluate MiGrATe on three challenging domains-word search, molecule optimization, and hypothesis+program induction on the Abstraction and Reasoning Corpus (ARC)-and find that it consistently outperforms both inference-only and TTT baselines, demonstrating the potential of online TTT as a solution for complex search tasks without external supervision.

cs.LG↗

arXiv2025

Steering AI-Driven Personalization of Scientific Text for General Audiences

Digital media platforms (e.g., science blogs) offer opportunities to communicate scientific content to general audiences at scale. However, these audiences vary in their scientific expertise, literacy levels, and personal backgrounds, making effective science communication challenging. To address this challenge, we designed TranSlider, an AI-powered tool that generates personalized translations of scientific text based on individual user profiles (e.g., hobbies, location, and education). Our tool features an interactive slider that allows users to steer the degree of personalization from 0 (weakly relatable) to 100 (strongly relatable), leveraging LLMs to generate the translations with chosen degrees. Through an exploratory study with 15 participants, we investigated both the utility of these AI-personalized translations and how interactive reading features influenced users' understanding and reading experiences. We found that participants who preferred higher degrees of personalization appreciated the relatable and contextual translations, while those who preferred lower degrees valued concise translations with subtle contextualization. Furthermore, participants reported the compounding effect of multiple translations on their understanding of scientific content. Drawing on these findings, we discuss several implications for facilitating science communication and designing steerable interfaces to support human-AI alignment.

cs.HC↗

arXiv2025

AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances

Large language models (LLMs) are being increasingly integrated into everyday products and services, such as coding tools and writing assistants. As these embedded AI applications are deployed globally, there is a growing concern that the AI models underlying these applications prioritize Western values. This paper investigates what happens when a Western-centric AI model provides writing suggestions to users from a different cultural background. We conducted a cross-cultural controlled experiment with 118 participants from India and the United States who completed culturally grounded writing tasks with and without AI suggestions. Our analysis reveals that AI provided greater efficiency gains for Americans compared to Indians. Moreover, AI suggestions led Indian participants to adopt Western writing styles, altering not just what is written but also how it is written. These findings show that Western-centric AI models homogenize writing toward Western norms, diminishing nuances that differentiate cultural expression.

cs.HC↗

arXiv2025

Sylber: Syllabic Embedding Representation of Speech from Raw Audio

Syllables are compositional units of spoken language that efficiently structure human speech perception and production. However, current neural speech representations lack such structure, resulting in dense token sequences that are costly to process. To bridge this gap, we propose a new model, Sylber, that produces speech representations with clean and robust syllabic structure. Specifically, we propose a self-supervised learning (SSL) framework that bootstraps syllabic embeddings by distilling from its own initial unsupervised syllabic segmentation. This results in a highly structured representation of speech features, offering three key benefits: 1) a fast, linear-time syllable segmentation algorithm, 2) efficient syllabic tokenization with an average of 4.27 tokens per second, and 3) novel phonological units suited for efficient spoken language modeling. Our proposed segmentation method is highly robust and generalizes to out-of-domain data and unseen languages without any tuning. By training token-to-speech generative models, fully intelligible speech can be reconstructed from Sylber tokens with a significantly lower bitrate than baseline SSL tokens. This suggests that our model effectively compresses speech into a compact sequence of tokens with minimal information loss. Lastly, we demonstrate that categorical perception-a linguistic phenomenon in speech perception-emerges naturally in Sylber, making the embedding space more categorical and sparse than previous speech features and thus supporting the high efficiency of our tokenization. Together, we present a novel SSL approach for representing speech as syllables, with significant potential for efficient speech tokenization and spoken language modeling.

cs.CL↗

arXiv2025

One Style Does Not Regulate All: Moderation Practices in Public and Private WhatsApp Groups

WhatsApp is the largest social media platform in the Global South and is a virulent force in global misinformation and political propaganda. Due to end-to-end encryption WhatsApp can barely review any content and mostly rely on volunteer moderation by group admins. Yet, little is known about how WhatsApp group admins manage their groups, what factors and values influence moderation decisions, and what challenges they face while managing their groups. To fill this gap, we interviewed admins of 32 diverse groups and reviewed content from 30 public groups in India and Bangladesh. We observed notable differences in the formation, members' behavior, and moderation of public versus private groups, as well as in how WhatsApp admins operate compared to those on other platforms. We used Baumrind's typology of 'parenting styles' as a lens to examine how admins enact care and control during volunteer moderation. We identified four styles based on how caring and controlling the admins are and discuss design recommendations to help them better manage problematic content in WhatsApp groups.

cs.HC↗

arXiv2024

Coding Speech through Vocal Tract Kinematics

Vocal tract articulation is a natural, grounded control space of speech production. The spatiotemporal coordination of articulators combined with the vocal source shapes intelligible speech sounds to enable effective spoken communication. Based on this physiological grounding of speech, we propose a new framework of neural encoding-decoding of speech -- Speech Articulatory Coding (SPARC). SPARC comprises an articulatory analysis model that infers articulatory features from speech audio, and an articulatory synthesis model that synthesizes speech audio from articulatory features. The articulatory features are kinematic traces of vocal tract articulators and source features, which are intuitively interpretable and controllable, being the actual physical interface of speech production. An additional speaker identity encoder is jointly trained with the articulatory synthesizer to inform the voice texture of individual speakers. By training on large-scale speech data, we achieve a fully intelligible, high-quality articulatory synthesizer that generalizes to unseen speakers. Furthermore, the speaker embedding is effectively disentangled from articulations, which enables accent-perserving zero-shot voice conversion. To the best of our knowledge, this is the first demonstration of universal, high-performance articulatory inference and synthesis, suggesting the proposed framework as a powerful coding system of speech.

eess.AS↗