Knowledge catalogue
arXiv:2605.02741v1 Announce Type: cross Abstract: The promise of Large Language Models in automated software engineering is often measured by functional correctness, overlooking the critical issue of
arXiv:2605.02289v1 Announce Type: new Abstract: Engineering problem solving is central to real-world decision-making, requiring mathematical formulations that not only represent complex problems but a
arXiv:2605.02913v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these syst
arXiv:2605.03196v1 Announce Type: new Abstract: A reliable language model should be able to signal, prior to generation, when a query falls outside its knowledge. We investigate whether representation
arXiv:2605.03971v1 Announce Type: new Abstract: Large Language Models (LLMs) are prone to factual hallucinations, risking their reliability in real-world applications. Existing hallucination detectors
arXiv:2605.01847v1 Announce Type: new Abstract: Outcome-only evaluation under-specifies whether an evaluated agent profile preserves the commitments required to solve a multi-turn task coherently. Neu
arXiv:2410.09457v2 Announce Type: replace Abstract: Modern cryptographic methods for implementing privacy-preserving LLMs such as gls{HE} require the LLMs to have a polynomial form. Forming such a rep
arXiv:2605.01471v1 Announce Type: cross Abstract: Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study o
arXiv:2605.02964v1 Announce Type: new Abstract: Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomou
arXiv:2605.03907v1 Announce Type: new Abstract: Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform
arXiv:2605.03314v1 Announce Type: new Abstract: In single-stream autoregressive interfaces, the same tokens both update the model state and constitute an irreversible public commitment. This coupling
arXiv:2603.27343v2 Announce Type: replace Abstract: Existing large language models (LLMs) evaluations use fixed-difficulty benchmarks that cannot adapt as models improve, and rarely isolate specific c
This article explains how retrieval quality directly impacts large language model performance in retrieval-augmented generation (RAG) systems, emphasizing that even advanced LLMs cannot produce better
arXiv:2509.00673v2 Announce Type: replace Abstract: We investigate the efficacy of Large Language Models (LLMs) in detecting implicit and explicit hate speech, examining how models with minimal safety
arXiv:2508.12535v3 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in
arXiv:2605.02073v1 Announce Type: new Abstract: Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reas
arXiv:2510.25426v2 Announce Type: replace Abstract: The rapid advancement of Large Language Models (LLMs) is positioning language at the core of human-computer interaction (HCI). We argue that advanci
arXiv:2605.01973v1 Announce Type: new Abstract: Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, appli
arXiv:2605.01047v1 Announce Type: cross Abstract: Hallucinations, outputs that sound plausible but are factually incorrect, remain an open challenge for deployed LLMs. In code generation, models frequ
arXiv:2605.02069v1 Announce Type: new Abstract: Many scoring applications require absolute predictions, while pairwise comparisons can provide a simpler learning objective. We present Pair2Score, a tw
Parllama is a TUI (Text UI) application designed for easy management and use of Ollama-based LLMs that also works with major cloud-provided LLMs. It provides core model management features including f
arXiv:2605.02236v1 Announce Type: cross Abstract: Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to m
arXiv:2605.01991v1 Announce Type: cross Abstract: Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a s
arXiv:2605.01708v1 Announce Type: cross Abstract: Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to better load-balance between the compute-bound
arXiv:2605.00974v1 Announce Type: cross Abstract: LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks th
arXiv:2605.00060v1 Announce Type: new Abstract: We present TADI (Tool-Augmented Drilling Intelligence), an agentic AI system that transforms drilling operational data into evidence-based analytical in
arXiv:2504.15077v5 Announce Type: replace Abstract: Large Language Models (LLMs) can translate natural language into SQL, but small models struggle with multi-table and complex queries in Zero-Shot Le
arXiv:2602.11083v2 Announce Type: replace Abstract: Remote change detection in LLMs is a difficult problem. Existing methods are either too expensive for deployment at scale, or require initial white-
arXiv:2605.00650v1 Announce Type: new Abstract: Fine-tuning LLMs is necessary for various dedicated downstream tasks, but classic backpropagation-based fine-tuning methods require substantial GPU memo
arXiv:2605.00435v1 Announce Type: new Abstract: Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping
arXiv:2605.00677v1 Announce Type: new Abstract: While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results ste
arXiv:2605.00505v1 Announce Type: cross Abstract: Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented g
arXiv:2601.05833v2 Announce Type: replace Abstract: Pretokenization is a crucial, sequential pass in Byte-level BPE tokenizers, yet little work has been done to optimize it for edge-side inference. Ou
arXiv:2605.00380v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diver
arXiv:2605.00140v1 Announce Type: cross Abstract: We present Activation Residual Hessian Quantization (ARHQ), a post-training weight splitting method designed to mitigate error propagation in low-bit
arXiv:2509.05291v2 Announce Type: replace-cross Abstract: Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, bec
arXiv:2604.27143v1 Announce Type: cross Abstract: Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based
arXiv:2604.27014v1 Announce Type: new Abstract: The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning
arXiv:2604.27972v1 Announce Type: new Abstract: Since the dawn of Trading Card Games, the genre has grown into a multi-billion-dollar industry engaging millions of analog and digital players worldwide
If you think you are going to get alignment out of LLMs you are sadly mistaken. If you live in a society in which people are rolling out LLMs at massive scale, without a robust solution to alignment (
arXiv:2604.27249v1 Announce Type: cross Abstract: When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts?
arXiv:2604.27335v1 Announce Type: new Abstract: Web filtering systems rely on accurate web content classification to block cyber threats, prevent data exfiltration, and ensure compliance. However, cla
arXiv:2604.27661v1 Announce Type: new Abstract: Detecting language ideologies is a valuable yet complex task for understanding how identities are constructed through discourse. In Luxembourg's multicu
arXiv:2604.28129v1 Announce Type: cross Abstract: Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where indi
arXiv:2604.26960v1 Announce Type: cross Abstract: Transformer-based agentic AI is rapidly being deployed on major platforms to help users shop, watch, and navigate content with less effort. While thes
arXiv:2601.11908v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with reasoning over long contexts where relevant information is sparsely distributed. Although plan-and-execut
arXiv:2604.27426v1 Announce Type: cross Abstract: Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although ''local offline
arXiv:2604.28048v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting p
arXiv:2601.08418v2 Announce Type: replace-cross Abstract: Tax code prediction is a crucial yet underexplored task in automating invoicing and compliance management for large-scale e-commerce platforms
arXiv:2604.26954v1 Announce Type: cross Abstract: Strategic model selection and reasoning settings are more effective than ensembling for optimizing automated scoring with large language models (LLMs)
arXiv:2604.27296v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bo
arXiv:2604.27221v1 Announce Type: new Abstract: Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and het
arXiv:2602.23163v3 Announce Type: replace Abstract: Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanis
arXiv:2604.26326v1 Announce Type: cross Abstract: Reinforcement learning (RL) has unlocked complex reasoning abilities in large language models (LLMs). However, most RL algorithms suffer from performa
arXiv:2604.25326v2 Announce Type: replace-cross Abstract: Speculative decoding enhances the inference efficiency of large language models (LLMs) by generating drafts using a small draft language model
arXiv:2604.26209v1 Announce Type: cross Abstract: Some text generation tasks, such as Attribute Value Extraction (AVE), require decoding multiple independent sequences from the same document context.
arXiv:2604.26880v1 Announce Type: new Abstract: Patient portals now give individuals direct access to their electronic health records (EHRs), yet access alone does not ensure patients understand or ac
arXiv:2604.26591v1 Announce Type: cross Abstract: Technology mapping is a critical yet challenging stage in logic synthesis. While Large Language Models (LLMs) have been applied to generate optimizati
arXiv:2604.26456v1 Announce Type: cross Abstract: The digitisation of classical Sanskrit literature is impeded by a scarcity of annotated resources, particularly for Named Entity Recognition. While re
arXiv:2604.25921v1 Announce Type: new Abstract: Large Language Models (LLMs) are trained to refuse harmful requests, yet they remain vulnerable to jailbreak attacks that exploit weaknesses in conversa