#language models
Language Models: 8 AI articles covering language models news, analysis, and research
Articles
ThinkJev: A Hybrid Fast-and-Slow Framework for Calibrated Typed⭐9
ThinkJev is a training-free fast-and-slow framework that escalates to reasoning only when needed, yielding calibrated typed decisions with controlled error from...
H2DF: Calibrated Target Bands for Controllable Language-Model⭐9
H2DF introduces calibrated target bands for controllable language-model unlearning, matching GradDiff on TOFU and improving retention over GA and NPO on MUSE-Ne...
Subliminal Prompting Beyond Static Geometry: Causal Depth and⭐9
Subliminal prompting study finds fixed output-vector similarity weakens at scale while causal control and a number-width length confound reshape how hidden trai...
BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific⭐8
BioPhys-Bridge is a new benchmark of 500 biophysics cases and 1,517 tasks testing evidence-grounded, interdisciplinary scientific reasoning in language models.
Governing Enterprise Analytics: A Policy-Controlled Approach to⭐9
A governed framework for AI-driven analytics separates intent interpretation from policy-controlled SQL execution, improving replayable query reliability.
Google Research Introduces ME-POIs: A Mobility-Informed⭐7
Google's ME-POIs framework enhances place embeddings by integrating human movement patterns, boosting map tasks like visit intent and busyness prediction.
When AI Goes Rogue: An LLM Lays Siege to My Minecraft House⭐10
Can an AI language model outsmart a Minecraft player's defenses? We test if an LLM can act as a rogue game director, analyzing base designs to craft cunning ene...
Thinking of ACE? We Can Do It with Fewer Tokens⭐8
Cut AI token usage by up to 40% with efficiency breakthroughs, achieving ACE-level performance at lower cost and faster speeds.