Papers with analytical tool
Adaptive Platt Scaling with Causal Interpretations for Self-Reflective Language Model Uncertainty Estimates (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new study examines the ability of large language models to self-monitor and ask for human intervention. |
| Approach: | They propose a formal analysis of LLM self-reflection for uncertainty estimation using domain adaptation theory. |
| Outcome: | The proposed method improves accuracy and human interpretation on reasoning tasks. |
Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse autoencoders (SAEs) have emerged as a powerful analytical tool in mechanistic interpretability for large language models (LLMs). |
| Approach: | They propose a novel approach that leverages SAEs to enhance the general in-context learning performance of large language models (LLMs). |
| Outcome: | The proposed method yields a 3.5% improvement across diverse text classification tasks and exhibits greater robustness to hyperparameter variations compared to standard steering approaches. |