LLMs & Texto — Radar de IA

TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter

arXiv:2607.28657v1 Announce Type: new Abstract: Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This work addresses the challenge by introducing a Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts with the explicit goal of improving downstream LLM performance. We train TAPR using reinforcement learning with Group Relative Policy Optimization (GRPO)...

03.08.2026

Blog LLMs & Texto

TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking

arXiv:2607.28680v1 Announce Type: new Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. Howeve...

03.08.2026

Blog LLMs & Texto

LARA: Lightweight Adapters in the Residual Stream for Composable Adaptation and Alignment

arXiv:2607.28669v1 Announce Type: new Abstract: We present LARA (Lightweight Additive Residual Adaptation), a method for efficient adaptation that operates in the residual stream of a frozen model rather than in its weights. Where LoRA adds an update of low rank to weight matrices, LARA reads the hidden state at a small set of layers and adds a correction of low rank back to the residual stream, leaving all base weights untouched. On a code fine-tuning task and on preference optimization (DPO), ...

03.08.2026

Blog LLMs & Texto

An Ontology-Guided, Deduplication-Aware Extraction Layer for Knowledge Graph Construction from Heterogeneous Documents

arXiv:2607.28662v1 Announce Type: new Abstract: Large language models extract entities and relationships from unstructured documents fluently but inconsistently: type vocabularies fracture across documents, the same person surfaces under several name variants, relationships duplicate, and distinct individuals who share a name risk silent conflation. This paper presents the design, implementation, and empirical refinement of a production extraction layer that converts a live document stream into ...

03.08.2026

Blog LLMs & Texto

Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review

arXiv:2607.28631v1 Announce Type: new Abstract: AI Scientist systems capable of autonomous research have the potential to significantly accelerate scientific discovery. However, evaluating and comparing the quality of AI-generated papers remains an open challenge. We propose and implement a rigorous benchmarking protocol using an automated peer-review system that harnesses frontier large language models to assess scientific papers across four core dimensions: originality, scientific rigor, clari...

03.08.2026

Blog LLMs & Texto

LLM Framework for Discovering Major Mathematical Conjectures: AI's Quest for the Next Riemann Hypothesis

arXiv:2607.28632v1 Announce Type: new Abstract: Major mathematical conjectures still depend heavily on expert intuition, so a unified method for the systematic generation and validation of conjectures with substantial mathematical potential remains unavailable. We present a three stage pipeline for major conjecture discovery, with region search from explicit local evidence modules, reflective validation for foundationality, novelty, and potential significance, and formal validation in Lean 4 and...

03.08.2026

Blog LLMs & Texto

Semantics of Subterfuge: Benchmarking Legal Deception Detection Against General-domain State-of-the-Art

arXiv:2607.29066v1 Announce Type: new Abstract: Deception detection has critical implications for legal proceedings, law enforcement, and online security. Although human judgment is limited in accuracy and scalability, Natural Language Processing (NLP) offers a data-driven alternative. We present a survey and comparative analysis of NLP-based Automatic Deception Detection (ADD) focusing on the legal domain, reviewing the evolution from feature-based machine learning to Large Language Model (LLM)...

03.08.2026

Blog Visão Computacional

RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning

arXiv:2607.29622v1 Announce Type: new Abstract: Visual imitation learning enables robots to acquire visuomotor skills directly from images, yet RGB observations lack explicit geometric cues, making learned policies brittle to camera perturbations. To address this, we propose \textbf{Ray-conditioned Vision Transformer Encoder (RayViT)}, a lightweight architecture that injects camera geometry into pretrained ViT backbones. RayViT represents camera geometry as a Pl\"ucker ray map, patchifies it int...

03.08.2026

Blog LLMs & Texto

Reasoning in Real World Clinical Care: Why Large Language Models Are Not Yet Safe for Autonomous Clinical Decision Support

arXiv:2607.28677v1 Announce Type: new Abstract: LLM now pass medical licensing examinations and, in curated cases, can rival physicians at diagnostic reasoning. These developments have accelerated the use of LLMs for symptom assessment and clinical decision support in diagnostic and treatment guidance, administrative documentation, and rules-based alert enhancement. This Perspective concerns the most consequential of these applications: the autonomous triage of self-presenting, undifferentiated ...

03.08.2026

Blog LLMs & Texto

Can LLMs Really Understand Item Difficulty Levels? Implications for Automated Item Generation Using LLMs

arXiv:2607.28634v1 Announce Type: new Abstract: The estimation of item difficulty plays a key role in both formative assessment and large-scale high-stakes summative assessments. This study explores how large language models (LLMs) perform in predicting item difficulty levels using items from a large-scale Reading and Writing test. The study investigated various prompting strategies and parameter settings across multiple LLMs. LLM performance was compared with encoder-only language models and fe...

03.08.2026

Blog LLMs & Texto

CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning

arXiv:2607.29172v1 Announce Type: new Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings. Following the LLM community, an emerging access paradigm for closed-weight robot foundation models is the managed supervised fine-tuning (SFT) API, where users submit training data and receive a tun...

03.08.2026

Blog LLMs & Texto

From Inline Notes to Collected Commentaries: Toward Context-Preserving Organization of Exegetical Knowledge in Classical Chinese Texts

arXiv:2607.29044v1 Announce Type: new Abstract: Inline notes and collected commentaries are important forms of scholarly communication that evolved within the Confucian exegetical tradition, yet have received little computational attention. Drawing on traditional Chinese exegetics and philology, this paper formulates collected commentary compilation as an NLP task and proposes a computational framework that preserves the contextual dependency of inline notes while enabling their automatic compil...

03.08.2026