Papers with analytical tool

2 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations