The paper investigates an LLM‑driven timbre generation interface, showing that the set of sounds a user can actually produce forms a zonotope whose dimension grows with each added sound, while the interface’s displayed position is often inaccurate. The error stems from both the model’s predicted coordinates and an interpolation step that is independent of model quality, leading to many refinement instructions that produce no perceptible change. The study concludes that effective agency (what users can do) and epistemic agency (what users can know) are separable and must be engineered independently, warning that silence can be misrepresented as success.
arXiv:2606. 05403v1 Announce Type: new Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions.
arXiv:2608. 19211v1 Announce Type: cross Abstract: Human speech is richly expressive, with prosody carrying linguistic and emotional information beyond the lexical content.
The Modality Maturity Index (MMI) is a new benchmark that evaluates large language models on their ability to handle five different modalities—text, image, audio, video, and document—across up to three-input and three-output combinations. It contains 893 self‑contained questions, each with human‑authored rubric criteria for the expected output modalities, and measures performance via an MMI Value and a Modality Presence Score (MPS). Experiments on five frontier multimodal models show low MPS scores, indicating limited modality availability, and confirm that LLM judges can reliably assess output correctness against human‑blind rubric scoring on 70.8% of cases.
The paper presents the first music‑specific, layer‑wise empirical study of hallucination in audio‑language models, framing it as a hierarchical perceptual grounding failure across five layers: sound events, temporal properties, tonal attributes, style, and emotion. It introduces MuseDiag, a diagnostic framework that evaluates nine models and finds universal vocal misperception, significant tonal perception differences, and identifies Audio‑Flamingo‑3 as the most stable model. The study also proposes two training‑free mitigation methods, ADD‑M and TPA, which reduce hallucination in probing but show variable effectiveness in free‑form generation, highlighting the need for multi‑paradigm evaluation.
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.
VeriPhy is an auditable physical‑verification system that transforms a text prompt into typed physical obligations and a statically validated execution plan before any video frames are generated. During execution, it gates calls to frozen low‑level experts (segmentation, tracking, counting, depth, OCR, audio‑event detection, etc.) and records provenance‑carrying evidence for each action. The system maps these records to a three‑valued state—supported, contradicted, or unknown—providing traceable verdicts that can be used to refine generation models.
The paper reviews the fragmented literature on real‑time voice agents, noting that architecture, turn‑taking, and agentic evaluation communities rarely cite each other. It presents three evidence‑based claims: (1) architecture choice is a deployment constraint rather than a definitive solution, (2) evaluation has shifted from component quality to grounded outcomes, and (3) the dyadic assumption is breaking down as multiparty turn‑taking and reasoning become essential. The authors propose the TRG reporting standard to characterize agents by timing, recovery, and state‑verified outcomes, with an optional fourth axis for multiparty contexts.
arXiv:2606. 09843v3 Announce Type: replace-cross Abstract: Large language models (LLMs) give stable answers to personality questionnaires, yet these self-reports fail to predict how the models behave.
arXiv:2609.14754v1 Announce Type: cross Abstract: Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an i...
VeriPhy is an auditable physical‑verification system that evaluates generated video by compiling prompts into typed physical obligations and a statically validated execution plan before any frames are observed. During execution, it gates calls to frozen low‑level experts (e.g., segmentation, tracking, counting, depth, OCR, audio‑event detection) and returns provenance‑carrying evidence records, which are mapped to a three‑valued state (supported, contradicted, unknown) with full traceability. On a 1,500‑clip corpus of human‑annotated flaw records, VeriPhy accounts for 228 failures out of 304, outperforming a published question‑decomposition evaluator that accounts for 164, while also providing auditable evidence for each verdict.
arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.