Logical Judgments Under Pressure: Diagnosing Syllogistic Stability with Learned Soft Prefixes

arXiv · Brian K Chen · 5d ago · 1 min · 0 views

Signal strength 10/100

To test how correct logical judgments respond to learned context, we prepend a soft prefix to an exactly labeled syllogistic reasoning benchmark while keeping the model fixed. Soft prefixes are opaque continuous vectors, so we characterize them through the…

PRISM indexes and ranks — it never republishes. The full piece lives with its author on arxiv.org.

Read on arxiv.org

#cs-ai #cs-cl #paper #ai

↳

Same wavelength

Stories the engine considers adjacent to this one.

Intelligence arXiv 2d ago

OpenForgeRL: Train Harness-native Agents in Any Environment

Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to external systems. While powerful, these complex harnesses also make agents hard to train end-to-end with…

1 min 0 views

Intelligence arXiv 2d ago

3D-Aware VLMs with Implicit and Explicit Geometries

Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning. To bridge this gap, we present VLM-IE3D, a unified…

1 min 0 views

Intelligence arXiv 2d ago

Beyond Sycophancy: Structured Resistance and Compliance in LLM Moral Reasoning

Building socially calibrated large language models, which can learn from others without simply yielding to them, requires more than reducing sycophancy as a one-dimensional failure mode. Models must distinguish when to incorporate others' perspectives from…

1 min 0 views

Intelligence arXiv 2d ago

MIRROR: Learning from the Other View for Multi-Modal Reasoning

Unlike large language models (LLMs) that exhibit strong reasoning capabilities, vision-language models (VLMs) struggle with visual reasoning, even on geometry problems that admit equivalent text, diagram, and combined diagram+text views. We show that these…

1 min 0 views