Designing and Interpreting Probes with Control Tasks

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2019

8 September 2019

Papers citing "Designing and Interpreting Probes with Control Tasks"

50 / 381 papers shown

Title
Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders Samuel Stevens Jacob Beattie T. Berger-Wolf Yu-Chuan Su 88 0 0 21 Nov 2025
Beyond Tokens in Language Models: Interpreting Activations through Text Genre Chunks Éloïse Benito-Rodriguez Einar Urdshals Jasmina Nasufi Nicky Pochinkov 88 0 0 20 Nov 2025
Spectral Identifiability for Interpretable Probe Geometry William Hao-Cheng Huang 97 0 0 20 Nov 2025
CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment Xue Jiang Yihong Dong Mengyang Liu Hongyi Deng Tian Wang ... Zhi Jin Wenpin Jiao Fei Huang Yongbin Li Ge Li 109 1 0 21 Oct 2025
When Annotators Disagree, Topology Explains: Mapper, a Topological Tool for Exploring Text Embedding Geometry and Ambiguity Nisrine Rair Alban Goupil Valeriu Vrabie Emmanuel Chochoy 117 0 0 20 Oct 2025
Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity Edward Y. Chang Ethan Chang 92 1 0 09 Oct 2025
Type and Complexity Signals in Multilingual Question Representations Robin Kokot Wessel Poelman 104 0 0 07 Oct 2025
Controllable Stylistic Text Generation with Train-Time Attribute-Regularized Diffusion Fan Zhou Chang Tian Tim Van de Cruys DiffM 105 1 0 07 Oct 2025
Probing the Difficulty Perception Mechanism of Large Language Models Sunbowen Lee Qingyu Yin Chak Tou Leong Jialiang Zhang Yicheng Gong Shiwen Ni Min Yang Xiaoyu Shen LRM 203 0 0 07 Oct 2025
Modeling Student Learning with 3.8 Million Program Traces Alexis Ross Megha Srivastava Jeremiah Blanchard Jacob Andreas 92 3 0 06 Oct 2025
Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional AttentionAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Zhaoxin Feng Jianfei Ma Emmanuele Chersoni Xiaojing Zhao Xiaoyi Bao 141 3 0 02 Oct 2025
From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens Hala Sheta Eric Huang Shuyu Wu Ilia Alenabi Jiajun Hong ... D. Wei Jialin Yang Jiawei Zhou Ziqiao Ma Freda Shi VLM 106 3 0 02 Oct 2025
Shape Happens: Automatic Feature Manifold Discovery in LLMs via Supervised Multi-Dimensional Scaling Federico Tiblias Irina Bigoulaeva Jingcheng Niu Simone Balloccu Iryna Gurevych 140 0 0 01 Oct 2025
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models James Oldfield Juil Sock Ioannis Patras Adel Bibi Fazl Barez 124 0 0 30 Sep 2025
Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT Guy Bar-Shalom Fabrizio Frasca Yaniv Galron Yftah Ziser Haggai Maron MLLM 115 0 0 30 Sep 2025
Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures Marco Bronzini Carlo Nicolini Bruno Lepri Jacopo Staiano Andrea Passerini LLMSV 104 0 0 29 Sep 2025
Language Model Planning from an Information Theoretic Perspective Muhammed Ustaomeroglu Baris Askin Gauri Joshi Carlee Joe-Wong Guannan Qu 117 0 0 28 Sep 2025
Towards Transparent AI: A Survey on Explainable Language Models Avash Palikhe Sribala Vidyadhari Chinta Zhipeng Yin Rui Guo Qiang Duan Jie Yang Wenbin Zhang 170 2 0 25 Sep 2025
A Pipeline to Assess Merging Methods via Behavior and Internals Yutaro Sigris Andreas Waldis MoMe 275 0 0 23 Sep 2025
Do Natural Language Descriptions of Model Activations Convey Privileged Information? Millicent Li Alberto Mario Ceballos Arroyo Giordano Rogers Naomi Saphra Byron C. Wallace 148 2 0 16 Sep 2025
Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories Liviu Nicolae Fircă Antonio Bărbălău Dan Oneata Elena Burceanu OOD VLM LRM 167 0 0 04 Sep 2025
Tracking World States with Language Models: State-Based Evaluation Using Chess Romain Harang Jason Naradowsky Yaswitha Gujju Yusuke Miyao 52 0 0 27 Aug 2025
What Does it Mean for a Neural Network to Learn a "World Model"? Kenneth Li F. Viégas Martin Wattenberg NAI 116 1 0 29 Jul 2025
The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability? Denis Sutter Julian Minder Thomas Hofmann Tiago Pimentel 184 9 0 11 Jul 2025
What Has a Foundation Model Found? Using Inductive Bias to Probe for World Models Keyon Vafa Peter G. Chang Ashesh Rambachan S. Mullainathan 601 14 0 09 Jul 2025
Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations Ananth Agarwal Jasper Jian Christopher D. Manning Shikhar Murty 235 1 0 20 Jun 2025
Enhancing Accuracy and Maintainability in Nuclear Plant Data Retrieval: A Function-Calling LLM Approach Over NL-to-SQL Mishca de Costa Muhammad Anwar Dave Mercier Mark Randall Issam Hammad 131 1 0 10 Jun 2025
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter EraAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Dan Oneaţă Desmond Elliott Stella Frank 183 2 0 04 Jun 2025
Echoes of BERT: Do Modern Language Models Rediscover the Classical NLP Pipeline? Michael Li Nishant Subramani KELM 224 1 0 02 Jun 2025
Different Speech Translation Models Encode and Translate Speaker Gender DifferentlyAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Dennis Fucci Marco Gaido Matteo Negri L. Bentivogli Marcely Zanon Boito Giuseppe Attanasio 217 1 0 02 Jun 2025
Understanding the learned look-ahead behavior of chess neural networks Diogo Cruz 304 0 0 26 May 2025
Large Language Models Do Multi-Label Classification Differently Marcus Ma Georgios Chochlakis Niyantha Maruthu Pandiyan Jesse Thomason Zengyi Qin 305 3 0 23 May 2025
Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization Vera Neplenbroek Arianna Bisazza Raquel Fernández 308 1 0 22 May 2025
Probing Subphonemes in Morphology ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Gal Astrach Yuval Pinter 275 0 0 16 May 2025
Designing and Contextualising Probes for African Languages Wisdom Aduah Francois Meyer 339 0 0 15 May 2025
Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations Yize Zhao Christos Thrampoulidis 277 0 0 13 May 2025
Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models Liyi Zhang Veniamin Veselovsky R. Thomas McCoy Thomas Griffiths 179 1 0 17 Apr 2025
Probing then Editing Response Personality of Large Language Models Tianjie Ju Zhenyu Shao Binghai Wang Yulin Chen Zhuosheng Zhang Hao Fei Yang Deng Wynne Hsu Sufeng Duan Gongshen Liu KELM 381 3 0 14 Apr 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 345 7 0 09 Apr 2025
Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models Zhanke Zhou Zhaocheng Zhu Xuan Li Mikhail Galkin Xiao Feng Sanmi Koyejo Jian Tang Bo Han LRM 421 11 0 28 Mar 2025
Construction Identification and Disambiguation Using BERT: A Case Study of NPN Wesley Scivetti Nathan Schneider 290 1 0 24 Mar 2025
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions Guy Bar-Shalom Fabrizio Frasca Derek Lim Yoav Gelberg Yftah Ziser Ran El-Yaniv Gal Chechik Haggai Maron 402 2 0 18 Mar 2025
Aligned Probing: Relating Toxic Behavior and Model Internals Andreas Waldis Vagrant Gautam Anne Lauscher Dietrich Klakow Iryna Gurevych 282 2 0 17 Mar 2025
Queueing, Predictions, and LLMs: Challenges and Open Problems Michael Mitzenmacher Rana Shahout AI4TS LRM 207 4 0 10 Mar 2025
Constructions are Revealed in Word Distributions J. Rozner Leonie Weissweiler Kyle Mahowald Cory Shain 338 4 0 08 Mar 2025
Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models Tianjie Ju Yi Hua Hao Fei Zhenyu Shao Yubin Zheng Haodong Zhao Yang Deng Wynne Hsu Zhuosheng Zhang Gongshen Liu 398 2 0 03 Mar 2025
A Close Look at Decomposition-based XAI-Methods for Transformer Language Models L. Arras Bruno Puri Patrick Kahardipraja Sebastian Lapuschkin Wojciech Samek 292 4 0 21 Feb 2025
Language Models Can Predict Their Own Behavior Dhananjay Ashok Jonathan May AI4TS ReLM LRM 414 5 0 18 Feb 2025
We Can't Understand AI Using our Existing Vocabulary John Hewitt Robert Geirhos Been Kim 307 13 0 11 Feb 2025
Mechanistic Interpretability of Emotion Inference in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Ala Nekouvaght Tak Amin Banayeeanzade Anahita Bolourani Mina Kian Robin Jia Jonathan Gratch 292 5 0 08 Feb 2025