Beware the Rationalization Trap! When Language Model Explainability
Diverges from our Mental Models of Language

Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language

14 July 2022

R. Sevastjanova

Mennatallah El-Assady

Papers citing "Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language"

8 / 8 papers shown

Title
Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis Matteo Esposito Francesco Palagiano Valentina Lenarduzzi Davide Taibi 90 6 0 11 Jun 2024
Why is "Problems" Predictive of Positive Sentiment? A Case Study of Explaining Unintuitive Features in Sentiment Classification Jiaming Qu Jaime Arguello Yue Wang FAtt 35 0 0 05 Jun 2024
generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation Thilo Spinner Rebecca Kehlbeck R. Sevastjanova Tobias Stähle Daniel A. Keim Oliver Deussen Mennatallah El-Assady 46 3 0 12 Mar 2024
SyntaxShap: Syntax-aware Explainability Method for Text Generation Kenza Amara R. Sevastjanova Mennatallah El-Assady 39 2 0 14 Feb 2024
RELIC: Investigating Large Language Model Responses using Self-Consistency Furui Cheng Vilém Zouhar Simran Arora Mrinmaya Sachan Hendrik Strobelt Mennatallah El-Assady HILM 19 18 0 28 Nov 2023
Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges Thilo Spinner Rebecca Kehlbeck R. Sevastjanova Tobias Stähle Daniel A. Keim Oliver Deussen Andreas Spitz Mennatallah El-Assady 32 2 0 17 Oct 2023
Characterizing Uncertainty in the Visual Text Analysis Pipeline P. Haghighatkhah Mennatallah El-Assady Jean-Daniel Fekete Narges Mahyar C. Paradis Vasiliki Simaki Bettina Speckmann 13 2 0 22 Sep 2022
What you can cram into a single vector: Probing sentence embeddings for linguistic properties Alexis Conneau Germán Kruszewski Guillaume Lample Loïc Barrault Marco Baroni 201 882 0 03 May 2018