January 2026

arXiv:2601.15338v1 Announce Type: new Abstract: Axial coding is a commonly used qualitative analysis method that enhances document understanding by organizing sentence-level open codes into broader categories. In this paper, we operationalize axial coding with large language models (LLMs). Extending an ensemble-based open coding approach with an LLM moderator, we add an axial coding step that groups open codes into higher-order categories, transforming raw debate transcripts into concise, hierarchical representations. We compare two strategies: (i) clustering embeddings of code-utterance […]

Ver mais

arXiv:2601.15337v1 Announce Type: new Abstract: Users should not be systemically disadvantaged by the language they use for interacting with LLMs; i.e. users across languages should get responses of similar quality irrespective of language used. In this work, we create a set of real-world open-ended questions based on our analysis of the WildChat dataset and use it to evaluate whether responses vary by language, specifically, whether answer quality depends on the language used to query the model. We also […]

Ver mais

arXiv:2601.15335v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to interact with external APIs, greatly enhancing their practical utility. While prior research has improved tool-calling performance by adopting traditional computer systems techniques, such as parallel and asynchronous execution, the challenge of redundant or repeated tool-calling requests remains largely unaddressed. Caching is a classic solution […]

Ver mais

arXiv:2601.15334v1 Announce Type: new Abstract: Whether language models possess sentience has no empirical answer. But whether they believe themselves to be sentient can, in principle, be tested. We do so by querying several open-weights models about their own consciousness, and then verifying their responses using classifiers trained on internal activations. We draw upon three model families (Qwen, Llama, GPT-OSS) ranging from 0.6 billion to 70 billion parameters, approximately 50 questions about consciousness and subjective experience, and three classification […]

Ver mais

arXiv:2601.15333v1 Announce Type: new Abstract: Large Language Models (LLMs) possess strong representation and reasoning capabilities, but their application to structure-based drug design (SBDD) is limited by insufficient understanding of protein structures and unpredictable molecular generation. To address these challenges, we propose Exploration-Augmented Latent Inference for LLMs (ELILLM), a framework that reinterprets the LLM generation process as an encoding, latent space exploration, and decoding workflow. ELILLM explicitly explores portions of the design problem beyond the model’s current knowledge while […]

Ver mais

arXiv:2601.15331v1 Announce Type: new Abstract: The deployment of large language models (LLMs) has raised security concerns due to their susceptibility to producing harmful or policy-violating outputs when exposed to adversarial prompts. While alignment and guardrails mitigate common misuse, they remain vulnerable to automated jailbreaking methods such as GCG, PEZ, and GBDA, which generate adversarial suffixes via training and gradient-based search. Although effective, these methods particularly GCG are computationally expensive, limiting their practicality for organisations with constrained resources. This […]

Ver mais

arXiv:2601.15330v1 Announce Type: new Abstract: Large Language Models (LLMs) in multi-turn conversations often suffer from a “lost-in-conversation” phenomenon, where they struggle to recover from early incorrect assumptions, particularly when users provide ambiguous initial instructions. We find that standard post-training techniques like Reinforcement Learning with Verifiable Rewards (RLVR) exacerbate this issue by rewarding confident, direct answers, thereby inducing overconfidence and discouraging the model from seeking clarification. To address this, we propose Illocution-Calibrated Policy Optimization (ICPO), a novel training framework […]

Ver mais

arXiv:2601.15327v1 Announce Type: new Abstract: In many competitive settings, from education to politics, rules do not reward effort evenly, and thresholds (e.g., grade cutoffs or electoral majorities) make some moments disproportionately important. Success thus depends on efficiently allocating limited resources. However, empirical demonstration has been difficult because effort allocation is rarely observable and feedback is often delayed, limiting our understanding of expertise. Professional tennis provides an ideal natural experiment. Because each game resets after a player wins four […]

Ver mais

arXiv:2601.15325v1 Announce Type: new Abstract: Dynamic community detection plays a crucial role in understanding the temporal evolution of community structures in complex networks. Existing methods based on nonnegative tensor RESCAL decomposition typically require the decomposition rank to equal the number of communities, which limits model flexibility. This paper proposes an improved MLP-enhanced nonnegative tensor decomposition model (MLP-NTD) that incorporates a multilayer perceptron (MLP) after RESCAL decomposition for community mapping, thereby decoupling the decomposition rank from the number of […]

Ver mais

arXiv:2601.15324v1 Announce Type: new Abstract: Adding memory to pretrained language models typically requires architectural changes or weight modification. We present Prometheus Mind, which retrofits memory to a frozen Qwen3-4B using 11 modular adapters (530MB, 7% overhead) — fully reversible by removing the adapters. Building this system required solving four problems: (1) Extraction — we develop Contrastive Direction Discovery (CDD), which finds semantic directions via minimal pairs without labeled data. (2) Training — end-to-end optimization collapses; stage-wise training of […]

Ver mais