VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
arXiv:2603.04822v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with nuanced human values remains a critical challenge, as existing methods like Reinforcement Learning from Human Feedback (RLHF) often handle only coarse-grained attributes. In practice, fine-tuning LLMs on task-specific datasets...
SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms
arXiv:2603.04873v1 Announce Type: new Abstract: Accurate time series forecasting underpins decision-making across domains, yet conventional ML development suffers from data scarcity in new deployments, poor adaptability under distribution shift, and diminishing returns from manual iteration. We propose Self-Evolving Agent for...
Differentially Private Multimodal In-Context Learning
arXiv:2603.04894v1 Announce Type: new Abstract: Vision-language models are increasingly applied to sensitive domains such as medical imaging and personal photographs, yet existing differentially private methods for in-context learning are limited to few-shot, text-only settings because privacy cost scales with the...
Alignment Backfire: Language-Dependent Reversal of Safety Interventions Across 16 Languages in LLM Multi-Agent Systems
arXiv:2603.04904v1 Announce Type: new Abstract: In perpetrator treatment, a recurring observation is the dissociation between insight and action: offenders articulate remorse yet behavioral change does not follow. We report four preregistered studies (1,584 multi-agent simulations across 16 languages and three...
Knowledge-informed Bidding with Dual-process Control for Online Advertising
arXiv:2603.04920v1 Announce Type: new Abstract: Bid optimization in online advertising relies on black-box machine-learning models that learn bidding decisions from historical data. However, these approaches fail to replicate human experts' adaptive, experience-driven, and globally coherent decisions. Specifically, they generalize poorly...
TimeWarp: Evaluating Web Agents by Revisiting the Past
arXiv:2603.04949v1 Announce Type: new Abstract: The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes? We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments...
Retrieval-Augmented Generation with Covariate Time Series
arXiv:2603.04951v1 Announce Type: new Abstract: While RAG has greatly enhanced LLMs, extending this paradigm to Time-Series Foundation Models (TSFMs) remains a challenge. This is exemplified in the Predictive Maintenance of the Pressure Regulating and Shut-Off Valve (PRSOV), a high-stakes industrial...
The Trilingual Triad Framework: Integrating Design, AI, and Domain Knowledge in No-code AI Smart City Course
arXiv:2603.05036v1 Announce Type: new Abstract: This paper introduces the "Trilingual Triad" framework, a model that explains how students learn to design with generative artificial intelligence (AI) through the integration of Design, AI, and Domain Knowledge. As generative AI rapidly enters...
WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
arXiv:2603.05044v1 Announce Type: new Abstract: Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a...
CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
arXiv:2603.04406v1 Announce Type: new Abstract: With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely on external rewards that often fail to...
Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge
arXiv:2603.04417v1 Announce Type: new Abstract: Large language models are increasingly used as automated evaluators in research and enterprise settings, a practice known as LLM-as-a-judge. While prior work has examined accuracy, bias, and alignment with human preferences, far less attention has...
Context-Dependent Affordance Computation in Vision-Language Models
arXiv:2603.04419v1 Announce Type: new Abstract: We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs). Through a large-scale computational study (n=3,213 scene-context pairs from COCO-2017) using Qwen-VL 30B and LLaVA-1.5-13B subject to systematic context priming across 7 agentic...
What Is Missing: Interpretable Ratings for Large Language Model Outputs
arXiv:2603.04429v1 Announce Type: new Abstract: Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization learn from direct rankings or numerical ratings of model outputs, these rankings are subjective, and a single numerical...
From Static Inference to Dynamic Interaction: Navigating the Landscape of Streaming Large Language Models
arXiv:2603.04592v1 Announce Type: new Abstract: Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged. However, existing definitions...
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning
arXiv:2603.04597v1 Announce Type: new Abstract: Large language models (LLMs) typically receive diverse natural language (NL) feedback through interaction with the environment. However, current reinforcement learning (RL) algorithms rely solely on scalar rewards, leaving the rich information in NL feedback underutilized...
iAgentBench: Benchmarking Sensemaking Capabilities of Information-Seeking Agents on High-Traffic Topics
arXiv:2603.04656v1 Announce Type: new Abstract: With the emergence of search-enabled generative QA systems, users are increasingly turning to tools that browse, aggregate, and reconcile evidence across multiple sources on their behalf. Yet many widely used QA benchmarks remain answerable by...
Stan: An LLM-based thermodynamics course assistant
arXiv:2603.04657v1 Announce Type: new Abstract: Discussions of AI in education focus predominantly on student-facing tools -- chatbots, tutors, and problem generators -- while the potential for the same infrastructure to support instructors remains largely unexplored. We describe Stan, a suite...
Optimizing Language Models for Crosslingual Knowledge Consistency
arXiv:2603.04678v1 Announce Type: new Abstract: Large language models are known to often exhibit inconsistent knowledge. This is particularly problematic in multilingual scenarios, where models are likely to be asked similar questions in different languages, and inconsistent responses can undermine their...
Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
arXiv:2603.04698v1 Announce Type: new Abstract: This paper evaluates data augmentation and feature enhancement techniques for hate speech detection, comparing traditional classifiers, e.g., Delta Term Frequency-Inverse Document Frequency (Delta TF-IDF), with transformer-based models (DistilBERT, RoBERTa, DeBERTa, Gemma-7B, gpt-oss-20b) across diverse datasets....
TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
arXiv:2603.04772v1 Announce Type: new Abstract: Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal multimodal embedding framework that...
Autoscoring Anticlimax: A Meta-analytic Understanding of AI's Short-answer Shortcomings and Wording Weaknesses
arXiv:2603.04820v1 Announce Type: new Abstract: Automated short-answer scoring lags other LLM applications. We meta-analyze 890 culminating results across a systematic review of LLM short-answer scoring studies, modeling the traditional effect size of Quadratic Weighted Kappa (QWK) with mixed effects metaregression....
SinhaLegal: A Benchmark Corpus for Information Extraction and Analysis in Sinhala Legislative Texts
arXiv:2603.04854v1 Announce Type: new Abstract: SinhaLegal introduces a Sinhala legislative text corpus containing approximately 2 million words across 1,206 legal documents. The dataset includes two types of legal documents: 1,065 Acts dated from 1981 to 2014 and 141 Bills from...
Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models
arXiv:2603.04893v1 Announce Type: new Abstract: Diverse outputs in text generation are necessary for effective exploration in complex reasoning tasks, such as code generation and mathematical problem solving. Such Pass@$k$ problems benefit from distinct candidates covering the solution space. However, traditional...
Decorrelating the Future: Joint Frequency Domain Learning for Spatio-temporal Forecasting
arXiv:2603.04418v1 Announce Type: new Abstract: Standard direct forecasting models typically rely on point-wise objectives such as Mean Squared Error, which fail to capture the complex spatio-temporal dependencies inherent in graph-structured signals. While recent frequency-domain approaches such as FreDF mitigate temporal...
Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes
arXiv:2603.04426v1 Announce Type: new Abstract: Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However, existing formulations struggle with narrow...
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
arXiv:2603.04427v1 Announce Type: new Abstract: Standard transformer attention uses identical dimensionality for queries, keys, and values ($d_q = d_k = d_v = \dmodel$). Our insight is that these components serve fundamentally different roles, and this symmetry is unnecessary. Queries and...
Uncertainty-Calibrated Spatiotemporal Field Diffusion with Sparse Supervision
arXiv:2603.04431v1 Announce Type: new Abstract: Physical fields are typically observed only at sparse, time-varying sensor locations, making forecasting and reconstruction ill-posed and uncertainty-critical. We present SOLID, a mask-conditioned diffusion framework that learns spatiotemporal dynamics from sparse observations alone: training and...
ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learning
arXiv:2603.04437v1 Announce Type: new Abstract: Federated learning (FL) enables multiple clients to collaboratively train a machine learning model without sharing their raw data. However, the limited computation resources of the clients may result in a high delay and energy consumption...
VSPrefill: Vertical-Slash Sparse Attention with Lightweight Indexing for Long-Context Prefilling
arXiv:2603.04460v1 Announce Type: new Abstract: The quadratic complexity of self-attention during the prefill phase impedes long-context inference in large language models. Existing sparse attention methods face a trade-off among context adaptivity, sampling overhead, and fine-tuning costs. We propose VSPrefill, a...
Understanding the Dynamics of Demonstration Conflict in In-Context Learning
arXiv:2603.04464v1 Announce Type: new Abstract: In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts,...