ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models
cs.CL
Submitted: 2025-10-15
Updated: 2025-10-15
Code: https://github.com/haziq-exe/ERGO
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
- Self-Refine: Iterative Refinement with Self-Feedback
- Steering Language Models With Activation Engineering
- Backtracking Improves Generation Safety
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data