Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

Audio language models are designed to understand speech, yet it remains unclear whether they capture how something is said beyond what is said. We present a mechanistic analysis of paralinguistic information in four open source models, Whisper-large-v2, Qwen2-Audio-7B Instruct, Qwen2.5-Omni-7B, and Chroma-4B, using the Expresso dataset with controlled speaking styles. We combine centered kernel alignment, linear probing with leave one speaker out evaluation, open ended tone prediction, and a content prosody leakage metric to trace how style information moves from the audio encoder to the final output. All models strongly encode speaking style in the late encoder, that is, the top third of the audio encoder's layers, but this information is consistently degraded before reaching the output. The projector reshapes representation geometry without removing information, while decoders differ in how much style they preserve depending on architecture and training objective. At the output level, models fall into two behaviors. Some are content driven, where predictions depend mainly on text. Others are acoustic driven, where predictions vary with speaking style. The leakage metric quantifies this difference, and qualitative results confirm it. Overall, we identify a gap between what models encode and what they use, highlighting a key limitation in current audio language models.

From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Decodability

How much of a vision-language model's (VLM) spatial understanding remains after the action post-training process of building a vision-language-action model (VLA)? We probe depth perception, a primitive of spatiogeometric understanding, from every decoder layer of a weight-matched open-source base VLM/VLA pair: Molmo2-ER and MolmoAct2-LIBERO. First, the VLA decodes depth worse at every layer, a persistent gap we call the floor. Second, the degradation is not uniform: while the base VLM's depth decodability improves through its final layers, the VLA's collapses, an additional late-layer drop we call the cliff. We causally localize the cliff to late-layer MLP interference: ablating the late-layer MLP writes recovers the majority of the terminal decodability cliff, while matched attention ablations and the same intervention in the weight-matched base VLM produce no comparable recovery. A module-level decomposition explains this dissociation: the base VLM carries depth most accessibly in accumulated MLP writes, whereas action post-training collapses depth decodability in the late accumulated writes.

The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs

Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting. We investigate whether this reflects missing internal knowledge or a gap between internal representations and verbalized outputs. Training simple probes on activations from four VLMs across five counting datasets reveals that nonlinear probes can reliably detect counting errors, suggesting that VLMs often encode the correct count even when they output the wrong answer. SVCCA analysis shows that probes trained on ground-truth counts and probes trained on model outputs occupy a partially shared activation subspace but read out along misaligned directions. We further validate our findings using a causal steering intervention, proving that strengthening the direction of count-identified probes does improve model counting performance. Motivated by this result, we propose a detector-guided self-correction method that selectively re-prompts the model only when an internal error detector predicts failure. This simple inference-time intervention improves counting accuracy by up to 15.6 absolute percentage points, without any parameter updates. Our results establish activation-based error probing as both a practical tool for improving VLM counting and a mechanistic lens on the gap between internal knowledge and model outputs.

Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing

Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring models to operate under a privileged modality setting, where auxiliary modalities are available only during training. While these modalities contain valuable information, existing MLLMs largely fail to leverage them effectively, as they treat modalities as interchangeable inputs rather than sources of complementary supervision. We propose Mixture of Probes (MoP), a novel framework that disentangles modality-specific and modality-general signals within the MLLM, allowing the model to preserve modality-dependent structure while learning transferable representations across modalities. At its core, MoP achieves this through a structured probing mechanism that extracts and organizes information from intermediate representations of a shared modality encoder, rather than relying only on final-layer alignment as done in existing MLLMs. To support this disentanglement, we further introduce MoP Cross-modal Training (MoP-X), a training strategy for MoP centered around a probe disentanglement loss that prevents probe collapse and encourages cross-modal learning. We evaluate MoP across two domains spanning eight tasks and four modalities under a comprehensive evaluation protocol tailored to the privileged modality setting, where each modality is independently treated as the sole input at inference time. MoP consistently outperforms strong MLLM baselines, achieving up to 65% relative improvement, demonstrating that auxiliary modalities, even when unavailable at inference, can provide substantial gains when effectively leveraged during training. Code, model checkpoints, and evaluation protocols will be made available at https://github.com/Sony/MoP.

Decodable Is Not Grounded: A Vision-Ablation Arbiter for VLM Spatial Reasoning

The standard way to read latent knowledge out of a model, a linear probe confirmed by a steering recovery, can systematically overstate what a vision-language model (VLM) actually grounds in the image. We show this on spatial reasoning, where the error is invisible to both probing and steering yet exposed by a one-line causal control: replacing the image with a gray blank. Probes decode the within-axis answer at 73--97% across axes, and a training-free projection lifts a near-chance axis from 59% to 79%, exactly the signature of unlocking latent knowledge. The blank-image arbiter refutes it, revealing three grounding regimes that probing conflates: an axis can be grounded (vision-dependent, correct), a prior (vision-independent, with its decode and its apparent recovery a directional default rather than perception), or, surprisingly, inverted: decodable, causally controllable, but deployed with the wrong sign, so the model scores below chance and the error requires looking. The taxonomy holds across the studied VLMs: in fourteen models spanning six language-model families and 2B--27B, horizontal is grounded, vertical is a prior, and depth is inverted, with the inversion emerging at scale within families. The decode-versus-deploy inversion replicates on seven of eight models across five families, and the minimal edit that re-deploys it varies with geometry: a training-free rotation matches a trained edit on the cleanest model, while distributed inversions need a trained low-rank edit, tracing a per-model correction-complexity spectrum. The cheap, self-calibrating arbiter cleanly separates grounded perception, inverted perception, and prior substitution; we argue it should be a default control for latent-knowledge and steering claims in VLMs.

Mirage Probes: How Vision Models Fake Visual Understanding

Vision-language models (VLMs) can answer image-based questions confidently, and often correctly, even when no image is provided. This mirage behavior inflates benchmark scores without reflecting visual grounding. Prior work treats this as a single failure mode. We argue it is two. Using Mirage Probes, a contrastive probing framework that pairs paraphrased question variants with matched mirage and non-mirage labels on the same image, we show that mirage behavior is linearly decodable from internal activations across residual stream, MLP, post-attention, and attention-head sites in two open-source VLMs. We demonstrate that a Naive Bayes text baseline cannot recover this signal, ruling out surface lexical confounds. Cross-benchmark separability patterns, together with a novel Prior Harnessing Index (PHI) measuring how much a model can answer from text alone, expose two distinct regimes: textual biases, where the model answers from language priors without engaging visual representations, and spurious images, where it constructs false visual content in latent space and answers as if grounded. The distinction has direct mitigation consequences: text-distribution cleaning can address the first regime but cannot reach the second, since spurious-image mirages live in the model's visual representations rather than its text. Faithful visual grounding will require interventions at the representational level.

When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models

Multimodal language models are typically evaluated through external behavior: selecting the correct image--text match, rejecting unsupported captions, or answering visual queries correctly. However, correct behavior alone does not show that the model's internal decision state remains stable under controlled semantic stress. We study this gap through S$^3$E (Structured Semantic Stress Evaluation), a framework for analyzing behavior-internal decoupling in multimodal language models. S$^3$E uses a positive-anchored A/B forced-choice setup in which an image-supported caption is contrasted against semantic stress candidates under both original and swapped option orders, while hidden states are extracted at the pre-answer decision state. We focus on strict-correct trials, where the model consistently selects the correct caption across both orders. Rather than treating arbitrary hidden-state variation as evidence of instability, we measure whether semantic-conflict candidates induce excess decision-state displacement relative to meaning-preserving controls. Across Qwen3VL, Gemma3, and InternVL3, semantic stress consistently produces positive selected-layer excess displacement over lexical controls despite correct forced-choice behavior, while comparisons against random negatives are model-dependent. We interpret this as a scoped decision-state stress-sensitivity signal rather than evidence of downstream failure or hallucination. Our results suggest that forced-choice correctness alone is not a sufficient certificate of invariant internal decision geometry.

Visual Instruction Tuning Aligns Modalities through Abstraction

Visual instruction tuning effectively adapts a pre-trained Large Language Model (LLM) to process image information alongside text. Yet, it remains unclear how visual features are embedded into the layer-wise hierarchy of abstractions of the LLM backbone. Across a diverse set of vision-language architectures, we show that instruction tuning primarily serves as a bridge, embedding visual features directly into the intermediate semantic layers of the LLM, bypassing the early layers devoted to unimodal processing. With probing analyses and causal interventions, we show that these intermediate layers are the semantic core of vision-language processing and play a critical role in the performance on a broad set of multimodal benchmarks. In addition, by comparing the geometry of semantically equivalent visual and textual representations, we find that fine-tuning extends and strengthens the existing abstraction phase, aligning visual features with pre-existing textual ones. Finally, we confirm the functional role of this localized alignment by restricting fine-tuning to intermediate layers alone: this strategy preserves the performance of full fine-tuning on vision-centric benchmarks while reducing training time. Our results suggest that multimodal integration is a localized phenomenon driven by the repurposing of the internal abstraction engine of the LLM.