← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Exposing the Achilles’ Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning ACL 2025
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis ACL 2025
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models ACL 2025
How do Transformer Embeddings Represent Compositions? A Functional Analysis ACL 2025
DynaCode: A Dynamic Complexity-Aware Code Benchmark for Evaluating Large Language Models in Code Generation ACL 2025
Towards the Law of Capacity Gap in Distilling Language Models ACL 2025
HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation ACL 2025
Language Models Resist Alignment: Evidence From Data Compression ACL 2025
On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings ACL 2025
PlanGenLLMs: A Modern Survey of LLM Planning Capabilities ACL 2025
On the Generalization vs Fidelity Paradox in Knowledge Distillation ACL 2025
Runtime Protocol Refinement Checking for Distributed Protocol Implementations NSDI 2025
M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation ACL 2025
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging ACL 2025
ProxAnn: Use-Oriented Evaluations of Topic Models and Document Clustering ACL 2025
EvolveBench: A Comprehensive Benchmark for Assessing Temporal Awareness in LLMs on Evolving Knowledge ACL 2025
Theoretical Guarantees for Minimum Bayes Risk Decoding ACL 2025
LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios ACL 2025
The Role of Deductive and Inductive Reasoning in Large Language Models ACL 2025
ACT: Knowledgeable Agents to Design and Perform Complex Tasks ACL 2025
Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable events ACL 2025
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking ACL 2025
Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models ACL 2025
Evaluating the Consistency of LLM Evaluators COLING 2025
Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding ACL 2025