Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline

26 May 2025

Papers citing "Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline"

27 / 27 papers shown

Title
Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models Mingyang Wang Heike Adel Lukas Lange Yihong Liu Ercong Nie Jannik Strötgen Hinrich Schütze HILM 100 5 0 05 Apr 2025
Do Multilingual LLMs Think In English? Lisa Schut Y. Gal Sebastian Farquhar 62 14 0 24 Feb 2025
The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities Zhaofeng Wu Xinyan Velocity Yu Dani Yogatama Jiasen Lu Yoon Kim AIFin 92 20 0 07 Nov 2024
The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling Ruochen Zhang Qinan Yu Matianyu Zang Carsten Eickhoff Ellie Pavlick 72 5 0 11 Oct 2024
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task Javier Ferrando Marta R. Costa-jussá 40 7 0 09 Oct 2024
Refusal in Language Models Is Mediated by a Single Direction Andy Arditi Oscar Obeso Aaquib Syed Daniel Paleka Nina Panickssery Wes Gurnee Neel Nanda 97 197 0 17 Jun 2024
How do Large Language Models Handle Multilingualism? Yiran Zhao Wenxuan Zhang Guizhen Chen Kenji Kawaguchi Lidong Bing LRM 73 76 0 29 Feb 2024
Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models Tianyi Tang Wenyang Luo Haoyang Huang Dongdong Zhang Xiaolei Wang Xin Zhao Furu Wei Ji-Rong Wen 78 59 0 26 Feb 2024
Do Llamas Work in English? On the Latent Language of Multilingual Transformers Chris Wendler V. Veselovsky Giovanni Monea Robert West 96 126 0 16 Feb 2024
Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs Bilal Chughtai Alan Cooney Neel Nanda HILM KELM 55 20 0 11 Feb 2024
Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models Asma Ghandeharioun Avi Caciularu Adam Pearce Lucas Dixon Mor Geva 91 113 0 11 Jan 2024
Steering Llama 2 via Contrastive Activation Addition Nina Rimsky Nick Gabrieli Julian Schulz Meg Tong Evan Hubinger Alexander Matt Turner LLMSV 57 210 0 09 Dec 2023
In-Context Learning Creates Task Vectors Roee Hendel Mor Geva Amir Globerson 83 160 0 24 Oct 2023
Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models Jirui Qi Raquel Fernández Arianna Bisazza KELM HILM 92 72 0 16 Oct 2023
Circuit Component Reuse Across Tasks in Transformer Language Models Jack Merullo Carsten Eickhoff Ellie Pavlick 76 70 0 12 Oct 2023
The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets Samuel Marks Max Tegmark HILM 134 216 0 10 Oct 2023
Low-Resource Languages Jailbreak GPT-4 Zheng-Xin Yong Cristina Menghini Stephen H. Bach SILM 85 200 0 03 Oct 2023
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model Kenneth Li Oam Patel Fernanda Viégas Hanspeter Pfister Martin Wattenberg KELM HILM 87 557 0 06 Jun 2023
Language Models Implement Simple Word2Vec-style Vector Arithmetic Jack Merullo Carsten Eickhoff Ellie Pavlick KELM 59 65 0 25 May 2023
Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting Haoyang Huang Tianyi Tang Dongdong Zhang Wayne Xin Zhao Ting Song Yan Xia Furu Wei LRM 67 174 0 11 May 2023
Finding Neurons in a Haystack: Case Studies with Sparse Probing Wes Gurnee Neel Nanda Matthew Pauly Katherine Harvey Dmitrii Troitskii Dimitris Bertsimas MILM 198 213 0 02 May 2023
Dissecting Recall of Factual Associations in Auto-Regressive Language Models Mor Geva Jasmijn Bastings Katja Filippova Amir Globerson KELM 243 313 0 28 Apr 2023
Eliciting Latent Predictions from Transformers with the Tuned Lens Nora Belrose Zach Furman Logan Smith Danny Halawi Igor V. Ostrovsky Lev McKinney Stella Biderman Jacob Steinhardt 58 225 0 14 Mar 2023
Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models Peter Hase Joey Tianyi Zhou Been Kim Asma Ghandeharioun MILM 93 184 0 10 Jan 2023
Language Models are Multilingual Chain-of-Thought Reasoners Freda Shi Mirac Suzgun Markus Freitag Xuezhi Wang Suraj Srivats ... Yi Tay Sebastian Ruder Denny Zhou Dipanjan Das Jason W. Wei ReLM LRM 238 363 0 06 Oct 2022
Locating and Editing Factual Associations in GPT Kevin Meng David Bau A. Andonian Yonatan Belinkov KELM 246 1,345 0 10 Feb 2022
First Align, then Predict: Understanding the Cross-Lingual Ability of Multilingual BERT Benjamin Muller Yanai Elazar Benoît Sagot Djamé Seddah LRM 46 75 0 26 Jan 2021