Article

Probing Hidden States for Calibrated, Alignment-Resistant Predictions in LLMs

2025-09-19

Abstract excerpt

Scientific applications of large language models (LLMs) demand reliable, well-calibrated predictions, but standard generative approaches often fail to fully access relevant knowledge contained in their internal representations. As a result, models appear less capable than they are, with useful information remaining latent. We present PING (Probing INternal states of Generative models), an open-source framework tha...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 20af905a-6547-50aa-ba2a-d6e94ba58edd
DOI: 10.1101/2025.09.17.25336018

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Probing Hidden States for Calibrated, Alignment-Resistant Predictions in LLMsDOI 10.1101/2025.09.17.25336018Read

Genomic Touchstone: Benchmarking Genomic Language Models in the Context of the Central DogmaSemantic proximity Read

Harnessing the Power of Single-Cell Large Language Models with Parameter Efficient Fine-Tuning using scPEFTSemantic proximity Read

Me-LLaMA: Foundation Large Language Models for Medical ApplicationsSemantic proximity Read

Large Language Models forecast Patient Health Trajectories enabling Digital TwinsSemantic proximity Read

Harnessing the Power of Single Cell Large Language Models with Parameter Efficient Fine-Tuning using scPEFTSemantic proximity Read

An Empirical Analysis of Fine-Tuning Large Language Models on Bioinformatics Literature: PRSGPT and BioStarsGPTSemantic proximity Read

Applications of ChatGPT/GPT4 in Biological Studies, Medical and Dental CareSemantic proximity Read

Generative AI and Language Models in Human Genetics and Health: From Variant Interpretation to Clinical Decision Support.Semantic proximity Read

Retrieval-Augmented Medical Large Language ModelsSemantic proximity Read

Semantic Calibration of Contextual Embedding in Large Language Model Generative Pathways Using Contextual-Distillation MechanismsSemantic proximity Read

Medical Large Language Models: Methods and ApplicationsSemantic proximity Read

A multi-modal cell-free RNA language model for liquid biopsy applicationsSemantic proximity Read