Knowledge catalogue
arXiv:2511.20104v2 Announce Type: replace Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed 'emergent
arXiv:2609.33812v1 Announce Type: cross Abstract: Repeated runs of the same coding agent are known to give different benchmark scores. We ask what that variation means for a team running an agent on i
arXiv:2604.22768v1 Announce Type: cross Abstract: Purpose: To design, implement, evaluate, and report on the regulatory requirements of a self-hosted LLM infrastructure for radiology adhering to the p
arXiv:2608.13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically
arXiv:2609.22208v1 Announce Type: new Abstract: Sofroniew et al. (2026) report that emotion concepts in Claude Sonnet 4.5 are represented as vectors whose geometry mirrors human affect psychology. We
arXiv:2609.23999v1 Announce Type: new Abstract: How large language models (LLMs) integrate patient risk with clinical cost tradeoffs remains poorly understood. We investigated how four open-weight LLM
arXiv:2605.26526v1 Announce Type: new Abstract: Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an ass
arXiv:2609.18106v1 Announce Type: cross Abstract: Open-weight large language models are rapidly entering hiring pipelines, yet their discriminatory failure modes -- and the regulatory exposure these c
arXiv:2609.14811v1 Announce Type: new Abstract: We introduce Crypto Accounting Bench (CAB), a benchmark for assessing whether frontier and open-weight language models can reconstruct the complete jour
arXiv:2609.14080v1 Announce Type: new Abstract: Promptable models such as microSAM segment electron microscopy (EM) images from point prompts, but automation requires generating prompts without user i
arXiv:2608.08634v1 Announce Type: new Abstract: Open-weight language models from Chinese AI labs caught up on benchmarks relative to proprietary frontier models in recent months. Yet their reliability
arXiv:2605.24383v1 Announce Type: new Abstract: Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to
arXiv:2610.07125v1 Announce Type: cross Abstract: While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important con
arXiv:2610.03124v1 Announce Type: cross Abstract: Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforc
arXiv:2609.40236v1 Announce Type: new Abstract: Converting free-text radiology reports into structured labels supports cohort building, quality assurance, and monitoring of clinical imaging models, bu
arXiv:2609.39437v1 Announce Type: new Abstract: Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coor
arXiv:2608.18086v1 Announce Type: new Abstract: The growth of open-weight foundation models (OWFMs) has prompted the AI community to re-evaluate strategies for effective downstream governance. Althoug
arXiv:2608.17202v1 Announce Type: new Abstract: Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in minute
arXiv:2608.17341v1 Announce Type: new Abstract: AI planning is concerned with finding a sequence of actions that achieves a specified goal. It relies on explicit models of the world, commonly represen
arXiv:2506.03259v3 Announce Type: replace Abstract: Purpose: To compare five lightweight open-weight large language models (LLMs) with a rule-based algorithm (RBA) and fine-tuned RadBERT for zero-shot
arXiv:2608.05420v1 Announce Type: cross Abstract: Large language models (LLMs) can generate text that resembles a mathematical proof, but resemblance does not establish correctness. A formal proof che
arXiv:2607.27421v1 Announce Type: new Abstract: Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable
arXiv:2605.11255v1 Announce Type: new Abstract: We present Hebatron, a Hebrew-specialized open-weight large language model built on the NVIDIA Nemotron-3 sparse Mixture-of-Experts architecture. Traini
arXiv:2605.00334v1 Announce Type: cross Abstract: Production agentic systems make many model calls per user request, and most of those calls are short, structured, and routine. This raises a practical
arXiv:2610.16835v1 Announce Type: cross Abstract: Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose four requirements: protection ef
arXiv:2610.09004v1 Announce Type: new Abstract: Does removing harmful information make open-weight models resistant to fine-tuning attacks? We show that mutual information at release alone cannot univ
arXiv:2610.09033v1 Announce Type: new Abstract: Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment rout
arXiv:2609.37902v1 Announce Type: new Abstract: Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored de
arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that p
arXiv:2609.16984v1 Announce Type: new Abstract: Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the res
arXiv:2609.16093v1 Announce Type: new Abstract: A shopping conversation has many routes to the same cart, and a task-success rate reduces all of them to one score. We build a deterministic and reprodu
arXiv:2609.05241v1 Announce Type: new Abstract: A rapidly expanding ecosystem of actors is removing built-in safety guardrails from open-weight AI models. We profile this ecosystem by identifying key
arXiv:2608.22176v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly applied to clinical prediction tasks such as in-hospital mortality and readmission from electronic health
arXiv:2608.22048v1 Announce Type: new Abstract: Large language models are increasingly deployed on local hardware for privacy, cost, and accessibility reasons. Yet many evaluations emphasize accuracy
arXiv:2608.20569v1 Announce Type: new Abstract: Are frontier models able to introspect about their internal states? Recent work suggests that under certain conditions a complex enough model can audit
arXiv:2608.15579v1 Announce Type: cross Abstract: Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long
arXiv:2608.15930v1 Announce Type: new Abstract: Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliab
arXiv:2607.22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produc
arXiv:2607.24259v1 Announce Type: new Abstract: Recent work has explored the use of Large Language Models (LLMs) to automate simulation model building, typically by generating executable code directly
arXiv:2607.21482v1 Announce Type: new Abstract: Large language models (LLMs) and agents are now widely used tools in code development, with data typically sent to third-party cloud-based models. Their
arXiv:2607.20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language
arXiv:2607.20058v1 Announce Type: new Abstract: Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the governing physics.
arXiv:2606.04739v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong potential for automated software vulnerability detection, particularly in retrieval-augmented generatio
arXiv:2606.04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5
arXiv:2604.22215v1 Announce Type: cross Abstract: Verbal confidence elicitation is widely used to extract uncertainty estimates from LLMs. We tested whether seven instruction-tuned open-weight models
arXiv:2510.14232v2 Announce Type: replace-cross Abstract: Competitive programming has become a rigorous benchmark for evaluating the reasoning and problem-solving capabilities of large language models
arXiv:2609.28007v1 Announce Type: new Abstract: Most Turkish-capable large language models (LLMs) are evaluated using general-purpose benchmarks rather than long, structurally complex domain documents
arXiv:2606.12821v2 Announce Type: replace Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis. New AI agents can be a helpful tool, but no benchmark
arXiv:2512.13374v2 Announce Type: replace Abstract: Recent advances in Large Language Models (LLMs) open new perspectives for automation in optimization, yet little is known about whether their intern
arXiv:2607.12077v1 Announce Type: new Abstract: Multi-agent language-model systems increasingly route local interactions, yet the runtime interaction graph is often treated as an implementation detail
arXiv:2606.31808v1 Announce Type: new Abstract: Language model systems built around proprietary APIs often operate on a token-based cost model. This becomes prohibitively expensive in the context of l
arXiv:2605.07209v1 Announce Type: cross Abstract: We introduce a proxy-analyzer framework for detecting hallucinations in large language models. Instead of looking inside the generating model, our sys
arXiv:2609.21879v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have recently been proposed as promising tools for face recognition, as they can produce natural language explanations a
arXiv:2608.25622v1 Announce Type: cross Abstract: Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executabl
arXiv:2607.13162v1 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by
arXiv:2606.26099v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in artificial intelligence (AI) governance analysis across national and international organisat
arXiv:2606.25605v1 Announce Type: new Abstract: Tool Calling and Structured Output are two core capabilities of modern Agent systems, yet their interaction under joint deployment conditions remains in
arXiv:2501.02211v2 Announce Type: replace-cross Abstract: Large language models (LLMs) reproduce homogeneity bias -- the tendency to portray marginalized groups as more internally similar than dominan
arXiv:2606.20959v1 Announce Type: new Abstract: Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdate
arXiv:2606.07721v1 Announce Type: new Abstract: Objectives: Automatic data extraction from free-text radiology reports enables large-scale research, but few studies assessed the performance of large l