February 2026

arXiv:2602.15868v1 Announce Type: new Abstract: Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic multi-tape Turing machine, where each tape represents a distinct component: input characters, tokens, vocabulary, model parameters, activations, probability distributions, and output text. The model enables precise localisation of failure modes to specific pipeline stages, revealing, e.g., how tokenisation obscures character-level structure needed for counting tasks. The model clarifies why techniques like chain-of-thought […]

Ver mais

arXiv:2602.15867v1 Announce Type: new Abstract: In this positioning paper, we evaluate the problem-solving and reasoning capabilities of contemporary Large Language Models (LLMs) through their performance in Zork, the seminal text-based adventure game first released in 1977. The game’s dialogue-based structure provides a controlled environment for assessing how LLM-based chatbots interpret natural language descriptions and generate appropriate action sequences to succeed in the game. We test the performance of leading proprietary models – ChatGPT, Claude, and Gemini – under […]

Ver mais

arXiv:2602.15866v1 Announce Type: new Abstract: Natural Language Processing (NLP) is integral to social media analytics but often processes content containing Personally Identifiable Information (PII), behavioral cues, and metadata raising privacy risks such as surveillance, profiling, and targeted advertising. To systematically assess these risks, we review 203 peer-reviewed papers and propose the NLP Privacy Risk Identification in Social Media (NLP-PRISM) framework, which evaluates vulnerabilities across six dimensions: data collection, preprocessing, visibility, fairness, computational risk, and regulatory compliance. Our analysis […]

Ver mais

arXiv:2602.15865v1 Announce Type: new Abstract: The integration of Artificial Intelligence (AI) necessitates determining whether systems function as tools or collaborative teammates. In this study, by synthesizing Human-AI Interaction (HAI) literature, we analyze this distinction across four dimensions: interaction design, trust calibration, collaborative frameworks and healthcare applications. Our analysis reveals that static interfaces and miscalibrated trust limit AI efficacy. Performance hinges on aligning transparency with cognitive workflows, yet a fluency trap often inflates trust without improving decision-making. Consequently, an […]

Ver mais

arXiv:2602.15864v1 Announce Type: new Abstract: Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations, which restrict global foresight and lead to inefficient exploration. In contrast, humans plan using maps: we reason globally first, then act locally. We introduce ReasonNavi, a human-inspired framework that operationalizes this reason-then-act paradigm by coupling Multimodal Large Language Models (MLLMs) with deterministic planners. ReasonNavi converts a top-down map into a discrete reasoning space by room segmentation and candidate […]

Ver mais

arXiv:2602.15863v1 Announce Type: new Abstract: Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However, the underlying mechanism behind these gains remains unclear, making it hard to decide when and how to apply the technique effectively. In this work, we argue that the key benefit arises not from the generated examples themselves but from the act of creating them. To validate […]

Ver mais

arXiv:2602.15862v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients despite high lexical scores (e.g., BLEU, ROUGE). To address this gap, we propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation. Our two-stage pipeline combines supervised fine-tuning (SFT) with reinforcement fine-tuning (RFT): SFT builds foundational accuracy using an Action-Reasoning dataset […]

Ver mais

arXiv:2602.15861v1 Announce Type: new Abstract: Text analysis of tabular data relies on two core operations: emph{summarization} for corpus-level theme extraction and emph{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks is their inability to meet the high standards of output stability demanded by data analytics. To address this challenge, we introduce textbf{CAST} (textbf{C}onsistency via textbf{A}lgorithmic Prompting and textbf{S}table textbf{T}hinking), a framework that enhances output stability by constraining the model’s latent reasoning […]

Ver mais

arXiv:2602.15860v1 Announce Type: new Abstract: Current neural reranking approaches for retrieval-augmented generation (RAG) rely on cross-encoders or large language models (LLMs), requiring substantial computational resources and exhibiting latencies of 3-5 seconds per query. We propose Maniscope, a geometric reranking method that computes geodesic distances on k-nearest neighbor (k-NN) manifolds constructed over retrieved document candidates. This approach combines global cosine similarity with local manifold geometry to capture semantic structure that flat Euclidean metrics miss. Evaluating on eight BEIR benchmark […]

Ver mais

arXiv:2602.15859v1 Announce Type: new Abstract: Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for accurate human hand-off – particularly in domains that depend heavily on real-time information. This paper presents an end-to-end framework for constructing and evaluating a conversational AI assistant directly from historical call transcripts. Incoming transcripts are first graded using a simplified adaptation of the PIPA framework, focusing on observation alignment and appropriate response […]

Ver mais