arXiv subjects

Sanika Chavan

Publications and source records attributed to Sanika Chavan.

4 recordsLinked to original sources

arXiv2026

Implicit Reasoning Steering via Concept Chaining

Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how final decisions are formed. We study whether this fragility can be exploited through implicit reasoning steering: using natural-language text to bias a model toward a designated answer without explicit instructions, triggers, or direct answer cues. Our approach, Concept Chaining, generates a short connection paragraph that links question entities to a target option through one or two intermediate concepts. We then continue pretraining a victim model on these connection paragraphs and evaluate whether its answer preference shifts on the original multiple-choice questions. Our results show that indirect, natural-looking text can systematically steer model predictions while remaining substantially less inferable than direct paraphrases, which shows that reasoning brittleness is not merely an evaluation artifact: it creates a practical channel through which latent biases can be amplified by ordinary-looking text to covertly redirect model decisions.

cs.CL↗

arXiv2026

Rhythm of the Deep: Two-Tier Combinatorial Structure in Sperm Whale Codas Revealed by Acoustic Unit Induction

Sperm-whale codas are conventionally described as recurring click-count and timing patterns. We show instead that their waveforms contain a two-tier combinatorial acoustic organization. Recurring click units combine with inter-click rhythm to form coda units, and recurring coda units exhibit additional sequence-level dependence under a different acoustic carrier. Using 1,483 recordings, eight families of frozen audio encoders induce click and coda inventories. Held-out transfer, matched nulls, destructive waveform counterfactuals, expert timing baselines, and explicit abstention separate supported structure from shared encoder shortcuts. Click-token composition predicts induced coda identity with a median normalized mutual-information lift of 0.380, including when events are detected without published click times or counts. Stable click order is weak, whereas rhythm predicts coda-representation distance after the exact click-token multiset is fixed. At the second tier, coda tokens show 0.132 bits of incremental lag-2 dependence under the prespecified categorical estimator. Two expert-inspired rhythm representations do not recover the positive component. Coda identity is also more tempo-stable than click identity. These results change the acoustic description of codas from a single prescribed rhythm inventory to layered waveform organization. The controlled-induction framework provides a general method for discovering and falsifying combinatorial structure in under-annotated audio.

cs.AI↗

arXiv2026

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-style indirect prompt/content-injection failure mode where that assumption breaks: a payload caught in plain English slips past the same detector when it is transported as structured float parameters and reconstructed only as fragmented telemetry. Across 14,400 attacked real-model trials on three commercial LLM APIs from different providers, the IFS-derived float-array carrier preserves 94.3% leakage ASR under the strongest dual-layer text-classifier defense evaluated in the main matrix: a Prompt Guard 2 + TF-IDF ensemble; the same carrier-level pattern also replicates with a fine-tuned roberta-base detector. We emphasize leakage ASR because downstream systems may act on quoted or reproduced markers even when the model refuses, but Strong ASR is the stricter metric for structurally compliant attack success. A 2 x 2 ablation shows that data-layer storage and reconstruction-layer fragmentation defeat different text views and that both are needed to evade both. A simple xxd detector and semantic validation block the current T3 instance, so the contribution is not an undetectable exploit but a measured failure boundary for text-only inspection in structured-input pipelines that expose reconstructed auxiliary channels to an LLM.

cs.CR↗

arXiv2026

VisAnalog: A Diagnostic Suite for Visual Concept Transfer on Natural Images

A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipulate concept-level properties under transformation and transfer them to new scenes. We introduce VisAnalog, a controlled suite for this setting on natural images. Each example instantiates $A\!:\!B::C\!:\,?$: images $B$ and a hidden target image $D$ are produced by applying the same deterministic transformation sequence to source images $A$ and $C$. Given $A$, $B$, and $C$, a model must answer a multiple-choice question about $D$. The benchmark contains 617 human-validated questions spanning one- to four-step transformations such as zoom, quadrant swap, rotation, flip, and hue rotation. Across strong proprietary and open-source VLMs, end-to-end accuracy is substantially lower than oracle accuracy when $D$ is directly shown, and degrades sharply as transformation depth increases, while human performance remains near the ceiling. A program-conditioned evaluation further separates failures of relation inference from failures of transformation application, showing that inferring the visual relation from $A \rightarrow B$ is the dominant bottleneck, with additional application errors emerging on harder multi-step cases. The dataset is publicly available at https://huggingface.co/datasets/zli99/VisAnalog.

cs.CV↗