Knowledge catalogue
arXiv:2605.07731v1 Announce Type: cross Abstract: This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE)
arXiv:2605.07153v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved remarkable success in LLM reasoning, but whether it can also improve direct recall of parametric knowledge rema
// LLMs Improving LLMs // Interesting progress the past of couple of weeks around self-improving AI agents. If autoresearch was interesting, you will like this read. (bookmark it) We've been hand-tuni
arXiv:2605.05615v2 Announce Type: replace Abstract: Large language models (LLMs) impose rapidly growing energy demands, creating an emerging energy and carbon crisis driven by large-scale inference. S
arXiv:2605.03884v1 Announce Type: new Abstract: Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-pr
arXiv:2603.18196v3 Announce Type: replace-cross Abstract: Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection aler
arXiv:2509.03540v3 Announce Type: replace Abstract: Large Language Models (LLMs) often struggle with producing factually consistent answers due to limitations in their parametric memory. Retrieval-Aug
arXiv:2605.01630v1 Announce Type: new Abstract: Rankings produced by holistic LLM-as-a-judge scoring are sensitive to the bias of the chosen judge model. We show that switching to binary rubric scorin
arXiv:2605.01017v1 Announce Type: new Abstract: We introduce Xiaohongshu Social Comparison Reader Elicitation (XHS-SCoRE), a reader-grounded benchmark for detecting if a text-only Xiaohongshu (RedNote
arXiv:2511.16767v2 Announce Type: replace Abstract: Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeli
Sebastian Raschka maintains a comprehensive gallery of LLM architecture diagrams and visualizations on his website, with higher-resolution versions available at sebastianraschka.com/llm-architecture-g
In this post, we introduce a systematic framework for LLM migration or upgrade in generative AI production, encompassing essential tools, methodologies, and best practices. The framework facilitates t
arXiv:2505.13766v5 Announce Type: replace-cross Abstract: Software Quality Assurance (SQA) is critical for delivering reliable, secure, and efficient software products. The Software Quality Assurance
arXiv:2604.25866v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in emotionally sensitive human-AI applications, yet little is known about how emotion recognition is
arXiv:2512.09972v5 Announce Type: replace-cross Abstract: Navigating the capability--efficiency trade-off in Large Language Models (LLMs) requires approximating a high-quality Pareto set. Existing mod
arXiv:2509.20374v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated strong performance across general NLP tasks, but their utility in automating numerical experime
arXiv:2506.04118v3 Announce Type: replace Abstract: We propose Guided Speculative Inference (GSI), a novel algorithm for efficient reward-guided decoding in large language models. GSI combines soft be
arXiv:2508.01191v5 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning (i.e., CoT reasoning) from large language models (
arXiv:2604.22939v1 Announce Type: cross Abstract: While the next-token prediction (NTP) paradigm enables large language models (LLMs) to express their intrinsic knowledge, its sequential nature constr
Thoughtful book on LLMs and linguistics — by someone who actually knows linguistics. Interested in the LLM vs. linguistic theory debate? My just out book will tell you (almost) all about it. https://m
arXiv:2604.22893v1 Announce Type: cross Abstract: Traditional data valuation methods based on ``row-count imes quality coefficient'' paradigms fail to capture the nuanced, nonlinear contributions that
Scaling massive monolithic LLMs continues to yield incredible results. But to truly unlock their ceiling, the next frontier is test-time compute and dynamic orchestration. Nature solves complex proble
图灵奖获得者、 AI 三大教父之一的 LeCun在达沃斯的发言，算是把整个硅谷的遮羞布扯了。 他说现在整个行业都被LLM彻底洗脑了，所有人都在同一条赛道上互相挖人，谁敢偏离主流谁就被骂落后。 这也是他离开Meta的真正原因，连Meta都已经LLM-pilled，他不想再跟风了。 最扎心的一句话是：纯生成式架构，不管是LLM、VLM还是VLA，永远造不出哪怕猫级的智能体。 因为它们本质上只是下一个t
arXiv:2509.21361v2 Announce Type: replace-cross Abstract: Large language model (LLM) providers boast big numbers for maximum context window sizes. To test the real world use of context windows, we 1)
arXiv:2604.21102v1 Announce Type: cross Abstract: We present a novel framework for automatically evaluating building conditions nationwide in the United States by leveraging large language models (LLM
arXiv:2510.20064v2 Announce Type: replace Abstract: Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection
arXiv:2604.08016v2 Announce Type: replace Abstract: Regardless of its foundational role in human discovery and sense-making, abductive reasoning--the inference of the most plausible explanation for an
arXiv:2604.19785v1 Announce Type: cross Abstract: Sensitive information, such as knowledge about an individual's personality, can be can be misused to influence behavior (e.g., via personalized messag
arXiv:2502.07963v4 Announce Type: replace-cross Abstract: Medical research faces well-documented challenges in translating novel treatments into clinical practice. Publishing incentives encourage rese
arXiv:2604.19204v1 Announce Type: cross Abstract: LLMs are increasingly being considered for prediction tasks in high-stakes social service settings, but their algorithmic fairness properties in this
arXiv:2601.15755v3 Announce Type: replace Abstract: Large language models are increasingly used to represent human opinions, values, or beliefs, and their steerability towards these ideals is an activ
arXiv:2604.19533v1 Announce Type: cross Abstract: We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of th
arXiv:2511.22099v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained sett
arXiv:2604.19015v1 Announce Type: cross Abstract: Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring
arXiv:2604.19167v1 Announce Type: cross Abstract: Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBL
arXiv:2604.18027v1 Announce Type: cross Abstract: Transpilation, or code translation, aims to convert source code from one programming language (PL) to another. It is beneficial for many downstream ap
arXiv:2604.16400v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the qua
arXiv:2601.14590v2 Announce Type: replace Abstract: Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine
arXiv:2510.11288v4 Announce Type: replace Abstract: Recent work has shown that narrow finetuning can produce broadly misaligned LLMs, a phenomenon termed emergent misalignment (EM). While concerning,
arXiv:2604.16612v1 Announce Type: new Abstract: Traffic prediction plays a central role in intelligent transportation systems (ITS) by supporting real-time decision-making, congestion management, and
arXiv:2604.18556v1 Announce Type: new Abstract: Weight quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-
arXiv:2604.16935v1 Announce Type: cross Abstract: Scarce longitudinal evidence examines LLMs' persuasiveness and humanness along time-evolving psychological frameworks. We introduce Talk2AI, a longitu
arXiv:2503.21248v3 Announce Type: replace Abstract: Large language models (LLMs) have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses r
arXiv:2510.09378v2 Announce Type: replace Abstract: Recent efforts to accelerate LLM pretraining have focused on computationally-efficient approximations that exploit second-order structure. This rais
arXiv:2604.15780v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in real-world applications, but even aligned models such as Mistral and LLaVA still exhibit unsafe b
arXiv:2604.15794v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable success, underpinning diverse AI applications. However, they often suffer from performance degra
arXiv:2604.15727v1 Announce Type: new Abstract: Large language models exhibit systematic limitations in structured logical reasoning: they conflate hypothesis generation with verification, cannot dist
arXiv:2506.02261v3 Announce Type: replace-cross Abstract: What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that e
arXiv:2408.15549v4 Announce Type: replace Abstract: As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional a
arXiv:2604.15140v1 Announce Type: new Abstract: We introduce DiscoTrace, a method to identify the rhetorical strategies that answerers use when responding to information-seeking questions. DiscoTrace
arXiv:2603.17512v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode
arXiv:2508.00222v5 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs
arXiv:2604.12179v1 Announce Type: new Abstract: Recent advancements in Large Language Models (LLMs) have improved their ability to process extended conversational contexts, yet fine-tuning and evaluat
arXiv:2604.12632v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) enhances LLM reasoning but often induces overconfidence, where incorrect responses yield lower perplexity th
arXiv:2409.06679v3 Announce Type: replace Abstract: Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and documen
arXiv:2604.11835v1 Announce Type: cross Abstract: Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of struc
arXiv:2506.07523v3 Announce Type: replace Abstract: Large language models (LLMs) seem to offer an easy path to interpretability: just ask them to explain their answers. Yet the features driving an ans
arXiv:2604.09748v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model's (LLM's) reasoning abi
arXiv:2604.09674v1 Announce Type: new Abstract: Do large language models (LLMs) think? Daniel Stoljar and Zhihe Vincent Zhang have recently developed an argument from rationality for the claim that LL
arXiv:2604.11120v1 Announce Type: new Abstract: Personality imbuing customizes LLM behavior, but safety evaluations almost always study prompt-based personas alone. We show this is incomplete: prompti