digitado

arXiv:2603.23533v1 Announce Type: new Abstract: RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction. We present MDKeyChunker, a three-stage pipeline for Markdown documents that (1) performs structure-aware chunking treating headers, code blocks, tables, and lists as atomic units; (2) enriches each chunk via a single LLM call extracting title, summary, keywords, typed entities, hypothetical questions, and a semantic key, while propagating […]

Ver mais

arXiv:2603.23532v1 Announce Type: new Abstract: This paper investigates whether structured representations can preserve the meaning of scientific sentences. To test this, a lightweight LLM is fine-tuned using a novel structural loss function to generate hierarchical JSON structures from sentences collected from scientific articles. These JSONs are then used by a generative model to reconstruct the original text. Comparing the original and reconstructed sentences using semantic and lexical similarity we show that hierarchical formats are capable of retaining information […]

Ver mais

arXiv:2603.23531v1 Announce Type: new Abstract: Political polarization emerges from a complex interplay of beliefs about policies, figures, and issues. However, most computational analyses reduce discourse to coarse partisan labels, overlooking how these beliefs interact. This is especially evident in online political conversations, which are often nuanced and cover a wide range of subjects, making it difficult to automatically identify the target of discussion and the opinion expressed toward them. In this study, we investigate whether Large Language Models […]

Ver mais

arXiv:2603.23530v1 Announce Type: new Abstract: Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled paradigm that combines verifiable formatting constraints with benchmark tasks of increasing complexity. Across three model families and over 8,000 prompts, compliance drops by 2-21% under concurrent task load. Vulnerability is highly type-dependent: terminal constraints (requiring action at the response boundary) degrade […]

Ver mais

arXiv:2603.23529v1 Announce Type: new Abstract: Large Language Models (LLMs) consistently under perform in low-resource linguistic contexts such as Konkani. This performance deficit stems from acute training data scarcity compounded by high script diversity across Devanagari, Romi and Kannada orthographies. To address this gap, we introduce Konkani-Instruct-100k, a comprehensive synthetic instruction-tuning dataset generated through Gemini 3. We establish rigorous baseline benchmarks by evaluating leading open-weights architectures including Llama 3.1, Qwen2.5 and Gemma 3 alongside proprietary closed-source models. Our primary […]

Ver mais

arXiv:2603.23528v1 Announce Type: new Abstract: The rapid proliferation of Large Language Models has created an environmental paradox: the very technology that could help solve climate challenges is itself becoming a significant contributor to global carbon emissions. We test whether prompt compression improves inference energy efficiency in 28,421 successful API trials (28,428 planned) across three providers (OpenAI GPT-4o-mini, Anthropic Claude-3.5-Sonnet, and DeepSeek-Chat), five benchmarks (HumanEval, MBPP, GSM8K, MATH, MMLU), and four compression ratios (r in {1.0, 0.7, 0.5, 0.3}). […]

Ver mais

arXiv:2603.23527v1 Announce Type: new Abstract: Prompt compression is often evaluated by input-token reduction, but its real deployment impact depends on how compression changes output length and total inference cost. We present a controlled replication and extension study of benchmark-dependent output dynamics under aggressive compression, covering 5,400 API calls across three benchmarks and multiple providers. To explain conflicting prior observations, we formalize instruction survival probability (Psi), a structural metric that captures whether task-critical prompt segments remain after truncation. Results […]

Ver mais

arXiv:2603.23526v1 Announce Type: new Abstract: The growing publication rate of research papers has created an urgent need for better ways to fact-check information, assess writing quality, and identify unverifiable claims. We present Plato’s Cave as an open-source, human-centered research verification system that (i) creates a directed acyclic graph (DAG) from a document, (ii) leverages web agents to assign credibility scores to nodes and edges from the DAG, and (iii) gives a final score by interpreting and evaluating the […]

Ver mais

arXiv:2603.23525v1 Announce Type: new Abstract: The economics of prompt compression depend not only on reducing input tokens but on how compression changes output length, which is typically priced several times higher. We evaluate this in a pre-registered six-arm randomized controlled trial of prompt compression on production multi-agent task-orchestration, analyzing 358 successful Claude Sonnet 4.5 runs (59-61 per arm) drawn from a randomized corpus of 1,199 real orchestration instructions. We compare an uncompressed control with three uniform retention rates […]

Ver mais

arXiv:2603.23524v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting top-activating examples, manually browsing individual features, or performing semantic search on interested concepts, which makes exploratory discovery of concepts difficult at scale. In this paper, we present Concept Explorer, a scalable interactive system for post-hoc exploration of SAE features that organizes concept explanations […]

Ver mais