← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts EMNLP 2025
Adaptively profiling models with task elicitation EMNLP 2025
Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions EMNLP 2025
Investigating How Pre-training Data Leakage Affects Models’ Reproduction and Detection Capabilities EMNLP 2025
The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFT EMNLP 2025
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks EMNLP 2025
Child-Directed Language Does Not Consistently Boost Syntax Learning in Language Models EMNLP 2025
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning EMNLP 2025
Evaluating the Evaluators: Are readability metrics good measures of readability? EMNLP 2025
From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors EMNLP 2025
Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic EMNLP 2025
Circuit Complexity Bounds for RoPE-based Transformer Architecture EMNLP 2025
Mind the Gap: How BabyLMs Learn Filler-Gap Dependencies EMNLP 2025
Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Making EMNLP 2025
Axioms for AI Alignment from Human Feedback AAAI 2025
Reason to Rote: Rethinking Memorization in Reasoning EMNLP 2025
The Bandit Whisperer: Communication Learning for Restless Bandits AAAI 2025
Batch Ensemble for Variance Dependent Regret in Stochastic Bandits AAAI 2025
Cost-Aware Near-Optimal Policy Learning AAAI 2025
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data EMNLP 2025
LLMs cannot spot math errors, even when allowed to peek into the solution EMNLP 2025
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving EMNLP 2025
How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmark EMNLP 2025
Can Large Language Models Win the International Mathematical Games? EMNLP 2025