Conditional probing: measuring usable information beyond a baseline

19 September 2021

John Hewitt

Kawin Ethayarajh

Percy Liang

Christopher D. Manning

ArXiv PDF HTML

Papers citing "Conditional probing: measuring usable information beyond a baseline"

40 / 40 papers shown

Title
A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models Liqiang Jing Guiming Hardy Chen Ehsan Aghazadeh Xin Eric Wang Xinya Du 48 0 0 04 May 2025
Linguistic Interpretability of Transformer-based Language Models: a systematic review Miguel López-Otal Jorge Gracia Jordi Bernad Carlos Bobed Lucía Pitarch-Ballesteros Emma Anglés-Herrero VLM 33 0 0 09 Apr 2025
Towards Reliable Evaluation of Behavior Steering Interventions in LLMs Itamar Pres Laura Ruis Ekdeep Singh Lubana David M. Krueger LLMSV 20 5 0 22 Oct 2024
Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5 Thao Anh Dang Limor Raviv Lukas Galke 18 1 0 15 Oct 2024
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem Qianli Wang Tatiana Anikina Nils Feldhus Simon Ostermann Sebastian Möller Vera Schmitt LRM 27 0 0 11 Sep 2024
The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding of Causal Interpretability Aaron Mueller Jannik Brinkmann Millicent Li Samuel Marks Koyena Pal ... Arnab Sen Sharma Jiuding Sun Eric Todd David Bau Yonatan Belinkov CML 35 18 0 02 Aug 2024
Free-text Rationale Generation under Readability Level Control Yi-Sheng Hsu Nils Feldhus Sherzod Hakimov 25 0 0 01 Jul 2024
Probing the Category of Verbal Aspect in Transformer Language Models Anisia Katinskaia R. Yangarber 40 1 0 04 Jun 2024
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting Suraj Anand Michael A. Lepori Jack Merullo Ellie Pavlick CLL 16 6 0 28 May 2024
Accurate and Nuanced Open-QA Evaluation Through Textual Entailment Peiran Yao Denilson Barbosa ELM 19 6 0 26 May 2024
DispaRisk: Assessing and Interpreting Disparity Risks in Datasets Jonathan Vasquez Carlotta Domeniconi Huzefa Rangwala 25 0 0 20 May 2024
RORA: Robust Free-Text Rationale Evaluation Zhengping Jiang Yining Lu Hanjie Chen Daniel Khashabi Benjamin Van Durme Anqi Liu 30 1 0 28 Feb 2024
RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations Jing-ling Huang Zhengxuan Wu Christopher Potts Mor Geva Atticus Geiger 53 24 0 27 Feb 2024
TVE: Learning Meta-attribution for Transferable Vision Explainer Guanchu Wang Yu-Neng Chuang Fan Yang Mengnan Du Chia-Yuan Chang ... Zirui Liu Zhaozhuo Xu Kaixiong Zhou Xuanting Cai Xia Hu 22 1 0 23 Dec 2023
Transformers as Graph-to-Graph Models James Henderson Alireza Mohammadshahi Andrei Catalin Coman Lesly Miculicich GNN 19 6 0 27 Oct 2023
Learning to Abstract with Nonparametric Variational Information Bottleneck Melika Behjati Fabio Fehr James Henderson SSL 16 1 0 26 Oct 2023
Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models You Li Jinhui Yin Yuming Lin 10 0 0 19 Oct 2023
Disentangling the Linguistic Competence of Privacy-Preserving BERT Stefan Arnold Nils Kemmerzell Annika Schreiner 10 0 0 17 Oct 2023
Measuring Information in Text Explanations Zining Zhu Frank Rudzicz FAtt 11 0 0 06 Oct 2023
Operationalising Representation in Natural Language Processing J. Harding 12 11 0 14 Jun 2023
Morphosyntactic probing of multilingual BERT models Judit Ács Endre Hamerlik Roy Schwartz Noah A. Smith András Kornai 19 9 0 09 Jun 2023
Gaussian Process Probes (GPP) for Uncertainty-Aware Probing Z. Wang Alexander Ku Jason Baldridge Thomas L. Griffiths Been Kim UQCV 18 11 0 29 May 2023
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness Archiki Prasad Swarnadeep Saha Xiang Zhou Mohit Bansal LRM 10 1 0 21 Apr 2023
Probing Graph Representations Mohammad Sadegh Akhondzadeh Vijay Lingam Aleksandar Bojchevski 26 10 0 07 Mar 2023
Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU? Jakub Ho'scilowicz Marcin Sowanski Piotr Czubowski Artur Janicki 15 2 0 27 Jan 2023
Trustworthy Social Bias Measurement Rishi Bommasani Percy Liang 21 10 0 20 Dec 2022
The Architectural Bottleneck Principle Tiago Pimentel Josef Valvoda Niklas Stoehr Ryan Cotterell 16 5 0 11 Nov 2022
REV: Information-Theoretic Evaluation of Free-Text Rationales Hanjie Chen Faeze Brahman Xiang Ren Yangfeng Ji Yejin Choi Swabha Swayamdipta 84 22 0 10 Oct 2022
OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization Zining Zhu Soroosh Shahtalebi Frank Rudzicz 13 4 0 25 Aug 2022
Latent Topology Induction for Understanding Contextualized Representations Yao Fu Mirella Lapata BDL 20 6 0 03 Jun 2022
Naturalistic Causal Probing for Morpho-Syntax Afra Amini Tiago Pimentel Clara Meister Ryan Cotterell MILM 98 18 0 14 May 2022
It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers Zheng Tang Mihai Surdeanu 11 6 0 25 Apr 2022
Probing for the Usage of Grammatical Number Karim Lasri Tiago Pimentel Alessandro Lenci Thierry Poibeau Ryan Cotterell 17 55 0 19 Apr 2022
Probing for Constituency Structure in Neural Language Models David Arps Younes Samih Laura Kallmeyer Hassan Sajjad 11 12 0 13 Apr 2022
Finding Structural Knowledge in Multimodal-BERT Victor Milewski Miryam de Lhoneux Marie-Francine Moens 12 9 0 17 Mar 2022
When classifying grammatical role, BERT doesn't care about word order... except when it matters Isabel Papadimitriou Richard Futrell Kyle Mahowald MILM 16 29 0 11 Mar 2022
Schrödinger's Tree -- On Syntax and Neural Language Models Artur Kulmizev Joakim Nivre 24 6 0 17 Oct 2021
A Closer Look at How Fine-tuning Changes BERT Yichu Zhou Vivek Srikumar 13 56 0 27 Jun 2021
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages Peng Qi Yuhao Zhang Yuhui Zhang Jason Bolton Christopher D. Manning AI4TS 184 1,638 0 16 Mar 2020
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 294 6,927 0 20 Apr 2018