13 citations · 19 across the 20 of their papers we have counts for
16 papers · 1 filter
The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
Yuan Cao, Mingyang Wang, Hinrich Schütze
Large language models (LLMs) are increasingly used as knowledge bases, but keeping them up to date requires targeted knowledge editing (KE). However, it remains unclear how edits a…
On the Entity-Level Alignment in Crosslingual Consistency
Yihong Liu, Mingyang Wang, François Yvon +1
Multilingual large language models (LLMs) are expected to recall factual knowledge consistently across languages. However, the factors that give rise to such crosslingual consisten…
BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
Philipp Mondorf, Mingyang Wang, Sebastian Gerstner +6
The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks…
Refusal Direction is Universal Across Safety-Aligned Languages
Xinpeng Wang, Mingyang Wang, Yihong Liu +2
Refusal mechanisms in large language models (LLMs) are essential for ensuring safety. Recent research has revealed that refusal behavior can be mediated by a single direction in ac…
Tracing Multilingual Factual Knowledge Acquisition in Pretraining
Yihong Liu, Mingyang Wang, Amir Hossein Kargaran +5
Large Language Models (LLMs) are capable of recalling multilingual factual knowledge present in their pretraining data. However, most studies evaluate only the final model, leaving…
Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes
Mingyang Wang, Lukas Lange, Heike Adel +3
Reasoning language models (RLMs) excel at complex tasks by leveraging a chain-of-thought process to generate structured intermediate steps. However, language mixing, i.e., reasonin…
Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
Qianli Wang, Mingyang Wang, Nils Feldhus +5
Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's effects on various LLM capabilit…
Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
Mingyang Wang, Heike Adel, Lukas Lange +4
Multilingual language models (MLMs) store factual knowledge across languages but often struggle to provide consistent responses to semantically equivalent prompts in different lang…
Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion
Mingyang Wang, Alisa Stoll, Lukas Lange +3
Adapting large language models (LLMs) to new and diverse knowledge is essential for their lasting effectiveness in real-world applications. This survey provides an overview of stat…
On Relation-Specific Neurons in Large Language Models
Yihong Liu, Runsheng Chen, Lea Hirlimann +6
In large language models (LLMs), certain \emph{neurons} can store distinct pieces of knowledge learned during pretraining. While factual knowledge typically appears as a combinatio…
Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
Mingyang Wang, Lukas Lange, Heike Adel +2
To ensure large language models contain up-to-date knowledge, they need to be updated regularly. However, model editing is challenging as it might also affect knowledge that is unr…
LangSAMP: Language-Script Aware Multilingual Pretraining
Yihong Liu, Haotian Ye, Chunlan Ma +2
Recent multilingual pretrained language models (mPLMs) often avoid using language embeddings -- learnable vectors assigned to individual languages. However, this places a significa…
How Transliterations Improve Crosslingual Alignment
Yihong Liu, Mingyang Wang, Amir Hossein Kargaran +6
Recent studies have shown that post-aligning multilingual pretrained language models (mPLMs) using alignment objectives on both original and transliterated data can improve crossli…
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
Ercong Nie, Bo Shao, Zifeng Ding +3
This paper introduces BMIKE-53, a comprehensive benchmark for cross-lingual in-context knowledge editing (IKE) across 53 languages, unifying three knowledge editing (KE) datasets:…
OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
Yihong Liu, Peiqin Lin, Mingyang Wang +1
Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary ext…
NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis
Mingyang Wang, Heike Adel, Lukas Lange +2
This paper describes our system developed for the SemEval-2023 Task 12 "Sentiment Analysis for Low-resource African Languages using Twitter Dataset". Sentiment analysis is one of t…