Knowledge catalogue
arXiv:2410.03296v4 Announce Type: replace Abstract: Instruction-tuned LLMs are able to provide extit{an} explanation about their output to users by generating self-explanations, without requiring the
arXiv:2605.20530v1 Announce Type: cross Abstract: Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evalu
arXiv:2605.20448v1 Announce Type: new Abstract: Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-c
arXiv:2605.21127v1 Announce Type: new Abstract: Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on or
arXiv:2605.20712v1 Announce Type: new Abstract: Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixin
arXiv:2605.20731v1 Announce Type: new Abstract: Text-to-image models produce graphic design at production scale, but their supervision comes from photo-style preference data with a single overall verd
arXiv:2605.21443v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing eval
arXiv:2605.21338v1 Announce Type: new Abstract: LLMs have demonstrated exceptional proficiency in a wide range of NLP tasks. However, a notable gap remains in practical data analysis scenarios, partic
arXiv:2605.21442v1 Announce Type: new Abstract: Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface f
arXiv:2605.19966v1 Announce Type: cross Abstract: Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perpl
arXiv:2605.20177v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is prima
arXiv:2605.19341v1 Announce Type: cross Abstract: Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across summarization,
arXiv:2605.18838v1 Announce Type: cross Abstract: Scaling laws predict loss from compute but not how capabilities interact. We measure the coupling between reasoning and truthfulness across 63 base mo
arXiv:2605.19127v1 Announce Type: new Abstract: LLM agents increasingly have access to private user data and act on the user's behalf when interacting with third-party systems. The user defines what m
arXiv:2605.18840v1 Announce Type: cross Abstract: Leaderboards rank frontier models on independent axes but do not reveal whether capabilities reinforce or trade off across releases -- and at the fron
arXiv:2605.19537v1 Announce Type: new Abstract: Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a per
arXiv:2605.20119v1 Announce Type: cross Abstract: We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters.
arXiv:2602.09805v2 Announce Type: replace-cross Abstract: As reasoning LLMs increasingly trade tokens for accuracy through deliberation, search, and self-correction, a single accuracy score can no lon
arXiv:2605.16613v1 Announce Type: new Abstract: We introduce a novel approach to emotion modeling that shifts the focus from identification to evaluation, addressing the limitations of discrete classi
arXiv:2605.17214v1 Announce Type: new Abstract: While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical
arXiv:2605.17295v1 Announce Type: cross Abstract: Modern reasoning agents are increasingly evaluated on their ability to generate multiple valid solution paths, plans, or tool-use traces for a given i
arXiv:2605.17792v1 Announce Type: new Abstract: Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir oper
arXiv:2605.16358v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly applied to forecasting. To evaluate this capability while mitigating pre-training data contamination, se
arXiv:2601.01685v2 Announce Type: replace-cross Abstract: As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an
arXiv:2602.11130v2 Announce Type: replace-cross Abstract: Sparse point clouds are a common input modality for 3D surface reconstruction, including in safety-critical settings such as surgical navigati
arXiv:2605.17364v1 Announce Type: new Abstract: Media bias detection has predominantly been framed as a classification task: assign a political label to an article or outlet. We argue this framing is
arXiv:2605.17283v1 Announce Type: cross Abstract: Recent progress in formal theorem proving has benefited from large-scale proof generation and verifier-aware training, but agentic proving is rarely i
arXiv:2510.18941v2 Announce Type: replace-cross Abstract: Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to task
arXiv:2605.18613v1 Announce Type: cross Abstract: Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio
arXiv:2504.13217v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have become increasingly embedded in organizational workflows. This has raised concerns over their energy consump
arXiv:2605.16410v1 Announce Type: new Abstract: Test-time scaling (TTS) methods have proven highly effective for LLMs, yet their application to vision-language models (VLMs) remains relatively underex
arXiv:2603.04161v2 Announce Type: replace Abstract: The False Belief Test (FBT) has been the main method for assessing Theory of Mind (ToM) and related socio-cognitive competencies. For Large Language
arXiv:2605.15217v1 Announce Type: new Abstract: Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representa
arXiv:2605.16215v1 Announce Type: new Abstract: Clinical decision support systems (CDSS) require scrutable, auditable pipelines that enable rigorous, reproducible validation. Yet current LLM-based CDS
arXiv:2510.02453v3 Announce Type: replace-cross Abstract: Frontier language models are deployed as black-box services, where model weights cannot be modified and customization is limited to prompting.
arXiv:2605.16023v1 Announce Type: new Abstract: LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its
arXiv:2605.15572v1 Announce Type: new Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characte
arXiv:2509.22739v3 Announce Type: replace-cross Abstract: Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the for
We built TERMS-Bench, a three-tier benchmark for LLM agents in real-world economic negotiation. No LLM-as-judge, no outcome rubrics: the environment itself is the verifier. 🏆Among frontier models, @An
arXiv:2605.14857v1 Announce Type: new Abstract: Harmonized System (HS) tariff classification is a high-stakes, expert-level task in which a free-form product description must be mapped to a specific s
arXiv:2605.14068v1 Announce Type: new Abstract: We introduce CurveBench, a benchmark for hierarchical topological reasoning from visual input. CurveBench consists of extbf{756 images} of pairwise non-
arXiv:2605.14621v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding
arXiv:2605.13997v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) layers route tokens through a handful of experts, and learning-free compression of these layers reduces inference cost
arXiv:2605.14259v1 Announce Type: new Abstract: Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Exis
arXiv:2605.14568v1 Announce Type: cross Abstract: Context. Behaviour-Driven Development (BDD) software test suites accumulate duplicated step subsequences. Three published refactoring patterns are ava
arXiv:2605.15081v1 Announce Type: cross Abstract: The development of high-quality text embeddings is increasingly drifting toward an exclusionary future, defined by three critical barriers: prohibitiv
arXiv:2605.14600v1 Announce Type: new Abstract: Scientific progress depends on sequences of enabling contributions, yet existing AI4Science benchmarks largely focus on citation prediction, literature
arXiv:2605.14115v1 Announce Type: new Abstract: Biomedical retrieval-augmented large language models (LLMs) often face evidence that is incomplete, misleading, or internally contradictory, yet evaluat
arXiv:2605.13412v1 Announce Type: cross Abstract: Off-the-shelf large language models (LLMs) are increasingly used to automate text annotation, yet their effectiveness remains underexplored for underr
arXiv:2601.13359v2 Announce Type: replace-cross Abstract: Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.g., 'Sure, here is how to
arXiv:2605.12684v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of thes
arXiv:2605.11224v1 Announce Type: new Abstract: Existing medical-agent benchmarks deliver imaging as pre-selected samples, never as an environment the agent must navigate. We introduce ABRA, a radiolo
arXiv:2605.11398v1 Announce Type: cross Abstract: We introduce AcuityBench, a benchmark for evaluating whether language models identify the appropriate urgency of care from user medical presentations.
arXiv:2605.11748v1 Announce Type: new Abstract: Bronchoscopy is routinely conducted in pulmonary clinics and intensive care units, but navigating the complex branching of the respiratory tract remains
arXiv:2605.11442v1 Announce Type: cross Abstract: Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digit
arXiv:2510.27055v2 Announce Type: replace Abstract: We present Contamination Detection via Context (CoDeC), a practical and accurate method to detect and quantify training data contamination in large
arXiv:2605.12128v1 Announce Type: new Abstract: Large language models are increasingly deployed in safety-critical applications, where their ability to resist harmful instructions is essential. Althou
arXiv:2605.11232v1 Announce Type: cross Abstract: Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements dif
arXiv:2605.11685v1 Announce Type: new Abstract: Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copy
arXiv:2605.11307v1 Announce Type: new Abstract: Image-to-code generation tests whether a vision-language model (VLM) can recover the structure of an image enough to express it as executable code. Exis