Copertina

Why Code, Why Now: An Information-Theoretic Perspective on the Limits of Machine Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Zhao, Zhimin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Why Softmax Attention Outperforms Linear Attention
di: Deng, Yichuan, et al.
Pubblicazione: (2023)

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective
di: Shao, Jintian, et al.
Pubblicazione: (2025)

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
di: Ni, Zanlin, et al.
Pubblicazione: (2026)

When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective
di: Zhang, Zelin, et al.
Pubblicazione: (2026)

Diagnosing Hate Speech Classification: Where Do Humans and Machines Disagree, and Why?
di: Yang, Xilin
Pubblicazione: (2024)

Why LLMs Cannot Think and How to Fix It
di: Jahrens, Marius, et al.
Pubblicazione: (2025)

Why Is RLHF Alignment Shallow? A Gradient Analysis
di: Young, Robin
Pubblicazione: (2026)

Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis
di: Gong, Shuzhi, et al.
Pubblicazione: (2026)

Why Are Linear RNNs More Parallelizable?
di: Merrill, William, et al.
Pubblicazione: (2026)

Why Larger Language Models Do In-context Learning Differently?
di: Shi, Zhenmei, et al.
Pubblicazione: (2024)

Generative Frontiers: Why Evaluation Matters for Diffusion Language Models
di: Pynadath, Patrick, et al.
Pubblicazione: (2026)

Unknown Unknowns: Why Hidden Intentions in LLMs Evade Detection
di: Srivastav, Devansh, et al.
Pubblicazione: (2026)

Why is prompting hard? Understanding prompts on binary sequence predictors
di: Wenliang, Li Kevin, et al.
Pubblicazione: (2025)

Why mask diffusion does not work
di: Sun, Haocheng, et al.
Pubblicazione: (2025)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
di: Kim, Jeonghye, et al.
Pubblicazione: (2026)

Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat
di: Aquino-Michaels, Keston
Pubblicazione: (2026)

Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
di: Zhang, Zheyuan, et al.
Pubblicazione: (2026)

Why Linear Interpretability Works: Invariant Subspaces as a Result of Architectural Constraints
di: Saurez, Andres, et al.
Pubblicazione: (2026)

Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph
di: Irie, Kazuki
Pubblicazione: (2024)

Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance
di: Goyal, Sachin, et al.
Pubblicazione: (2024)

Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
di: Bi, Jing, et al.
Pubblicazione: (2025)

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
di: Frank, Gregory N.
Pubblicazione: (2026)

Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
di: Kumar, Anantha Padmanaban Krishna
Pubblicazione: (2025)

Why Do Safety Guardrails Degrade Across Languages?
di: Zhang, Max, et al.
Pubblicazione: (2026)

FADE: Why Bad Descriptions Happen to Good Features
di: Puri, Bruno, et al.
Pubblicazione: (2025)

Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs
di: Billa, Jayadev
Pubblicazione: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
di: Català, Mar Gonzàlez I, et al.
Pubblicazione: (2026)

Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis
di: Chiang, Jeffrey Yang Fan, et al.
Pubblicazione: (2025)

Why Bonds Fail Differently? Explainable Multimodal Learning for Multi-Class Default Prediction
di: Lu, Yi, et al.
Pubblicazione: (2025)

Why Don't Prompt-Based Fairness Metrics Correlate?
di: Zayed, Abdelrahman, et al.
Pubblicazione: (2024)

Why Any-Order Autoregressive Models Need Two-Stream Attention: A Structural-Semantic Tradeoff
di: Pynadath, Patrick, et al.
Pubblicazione: (2026)

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
di: Choi, Yumin, et al.
Pubblicazione: (2025)

Why is "Chicago" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues
di: Qu, Jiaming, et al.
Pubblicazione: (2025)

Why Should This Article Be Deleted? Transparent Stance Detection in Multilingual Wikipedia Editor Discussions
di: Kaffee, Lucie-Aimée, et al.
Pubblicazione: (2023)

When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
di: Tao, Hongyi, et al.
Pubblicazione: (2026)

When Fairness Isn't Statistical: The Limits of Machine Learning in Evaluating Legal Reasoning
di: Barale, Claire, et al.
Pubblicazione: (2025)

An Information Theoretic Perspective on Agentic System Design
di: He, Shizhe, et al.
Pubblicazione: (2025)

Reranking Laws for Language Generation: A Communication-Theoretic Perspective
di: Farinhas, António, et al.
Pubblicazione: (2024)

Learning from Negative Examples: Why Warning-Framed Training Data Teaches What It Warns Against
di: Enkhbayar, Tsogt-Ochir
Pubblicazione: (2025)

On the Theoretical Limitations of Embedding-Based Retrieval
di: Weller, Orion, et al.
Pubblicazione: (2025)