Natural Language Processing (NLP)

2 items

RESEARCHarXiv CS.CL·4/15/2026

Robust Explanations for User Trust in Enterprise NLP Systems

This research proposes a unified black-box robustness evaluation framework for token-level explanations to improve user trust in enterprise NLP systems, especially when migrating to LLMs. It operationalizes robustness via top-token flip rate under realistic perturbations, conducting a systematic comparison across various encoder and decoder architectures like BERT, RoBERTa, Qwen, and Llama.

model robustness Explainable AI (XAI)User Trust Large Language Models (LLMs)

RESEARCHarXiv CS.CL·4/21/2026

Brain-CLIPLM: Decoding Compressed Semantic Representations in EEG for Language Reconstruction

This work proposes a semantic compression hypothesis to overcome limitations in EEG-to-text decoding, suggesting that EEG signals encode compressed semantic anchors rather than full linguistic structure. It introduces Brain-CLIPLM, a two-stage framework for semantic anchor extraction via contrastive learning and sentence reconstruction using a retrieval-grounded large language model.

Brain-Computer Interface (BCI)deep learning Machine Learning Natural Language Processing (NLP)