Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions

6 May 2024

Papers citing "Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions"

8 / 8 papers shown

Title
MIB: A Mechanistic Interpretability Benchmark Aaron Mueller Atticus Geiger Sarah Wiegreffe Dana Arad Iván Arcuschin ... Alessandro Stolfo Martin Tutek Amir Zur David Bau Yonatan Belinkov 51 1 0 17 Apr 2025
Mitigating Selection Bias with Node Pruning and Auxiliary Options Hyeong Kyu Choi Weijie Xu Chi Xue Stephanie Eckman Chandan K. Reddy 31 1 0 27 Sep 2024
Talking Heads: Understanding Inter-layer Communication in Transformer Language Models Jack Merullo Carsten Eickhoff Ellie Pavlick 58 13 0 13 Jun 2024
Finding Neurons in a Haystack: Case Studies with Sparse Probing Wes Gurnee Neel Nanda Matthew Pauly Katherine Harvey Dmitrii Troitskii Dimitris Bertsimas MILM 162 188 0 02 May 2023
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model Michael Hanna Ollie Liu Alexandre Variengien LRM 193 121 0 30 Apr 2023
Dissecting Recall of Factual Associations in Auto-Regressive Language Models Mor Geva Jasmijn Bastings Katja Filippova Amir Globerson KELM 191 266 0 28 Apr 2023
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Kevin Wang Alexandre Variengien Arthur Conmy Buck Shlegeris Jacob Steinhardt 212 497 0 01 Nov 2022
Leveraging Large Language Models for Multiple Choice Question Answering Joshua Robinson Christopher Rytting David Wingate ELM 146 186 0 22 Oct 2022