565 citations · 610 across the 78 of their papers we have counts for
79 papers · 1 filter
Predicting Linear Relational Decodability Without the Relation
Jonas Rohweder, Adrian Mülthaler, Faridoun Mehri +3
Linear relational embeddings (LREs) approximate a language model's subject-to-object mapping with an affine function. Their faithfulness varies enormously across relations, from ne…
Beyond Clean Accuracy: The Practical Challenges and Benefits of Pixel-Based Language Models
Haowen Tang, Wei Xia, Raoyuan Zhao +2
Pixel-based language models process rendered text without relying on a fixed subword vocabulary, offering a promising approach to noisy and multilingual inputs. However, their prac…
Knowledge That Is Linear Before Fine-Tuning Generalizes After It
Faridoun Mehri, Hinrich Schütze
Not all facts a language model can recall support further learning equally well. We distinguish active facts, which support generalization beyond their own recall, from inert facts…
Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging
Zijing Wang, Yongkang Liu, Mingyang Wang +8
Merging pretrained models has emerged as an effective approach for consolidating diverse capabilities into a single unified model. However, prevailing merging methods typically tre…
Beyond Input Understanding: Diagnosing Multilingual Mathematical Reasoning with Directed Acyclic Trace Graphs
Jiaqiao Zhang, Zhoujun Li, Zhuojun Li +6
Large reasoning models (LRMs) achieve strong mathematical reasoning performance in English, but remain much less reliable in many low- and medium-resource languages. This gap is of…
ReverseMath: Answer Inversion for Scalable and Verifiable Mathematical Problem Generation
Raoyuan Zhao, Yihong Liu, Yupei Du +2
Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evaluation and training pipelines…
DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
Zijing Wang, Mingyang Wang, Ercong Nie +6
Towards more general and human-like intelligence, large language models should seamlessly integrate both multilingual and multimodal capabilities; however, extending an existing mu…
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
Yihong Liu, Raoyuan Zhao, Michael A. Hedderich +1
Large language models (LLMs) have achieved remarkable progress in mathematical reasoning, but this ability is not equally accessible across languages. Especially low-resource langu…
GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts
Amir Hossein Kargaran, Nafiseh Nikeghbal, Jana Diesner +2
Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cluster of high- and mid-resou…
Do We Still Need Humans in the Loop? Human vs. LLM Annotation in Active Learning for TikTok Hate Speech Detection
Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein +1
Annotating data remains a costly bottleneck for supervised NLP. Active learning (AL) reduces the number of human labels needed by selecting only the most informative instances, whi…
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…
Evaluating Contextually Mediated Factual Recall in Multilingual Large Language Models
Yihong Liu, Bingyu Xiong, Hinrich Schütze
Large language models (LLMs) can recall a wide range of factual knowledge across languages. However, existing factual recall evaluations primarily assess fact retrieval in isolatio…
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
Zijing Wang, Yongkang Liu, Mingyang Wang +8
Multimodal Large Language Models (MLLMs) rely on strong linguistic reasoning inherited from their base language models. However, multimodal instruction fine-tuning paradoxically de…
High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
Yongkang Liu, Xing Li, Mengjie Zhao +7
As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation…
SAD: A Large-Scale Strategic Argumentative Dialogue Dataset
Yongkang Liu, Jiayang Yu, Mingyang Wang +6
Argumentation generation has attracted substantial research interest due to its central role in human reasoning and decision-making. However, most existing argumentative corpora fo…
Left, Right, or Center? Evaluating LLM Framing in News Classification and Generation
Molly Kennedy, Ali Parker, Yihong Liu +1
Large Language Model (LLM) based summarization and text generation are increasingly used for producing and rewriting text, raising concerns about political framing in journalism wh…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
Relational Linearity is a Predictor of Hallucinations
Yuetian Lu, Yihong Liu, Sebastian Gerstner +3
Hallucination is a central failure mode of language models (LMs). We focus on hallucinations in response to questions like: "Which instrument did Glenn Gould play?", but we ask the…
Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations
Yuxi Xia, Dennis Ulmer, Terra Blevins +3
Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing evaluations mainly concern the align…
Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners
Yihong Liu, Raoyuan Zhao, Hinrich Schütze +1
Large reasoning models (LRMs) achieve strong performance on mathematical reasoning tasks, often attributed to their capability to generate explicit chain-of-thought (CoT) explanati…
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
Qianli Wang, Van Bach Nguyen, Yihong Liu +6
Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language model…
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…
A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages
Raoyuan Zhao, Yihong Liu, Hinrich Schütze +1
Large reasoning models (LRMs) increasingly rely on step-by-step Chain-of-Thought (CoT) reasoning to improve task performance, particularly in high-resource languages such as Englis…
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…