565 citations · 610 across the 78 of their papers we have counts for
28 papers · 1 filter
Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering
Jian Lan, Zhicheng Liu, Udo Schlegel +5
Large vision-language models (VLMs) achieve strong performance in Visual Question Answering but still rely heavily on supervised fine-tuning (SFT) with massive labeled datasets, wh…
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…
Evaluating Robustness of Large Language Models Against Multilingual Typographical Errors
Raoyuan Zhao, Yihong Liu, Lena Altinger +2
Large language models (LLMs) are increasingly deployed in multilingual, real-world applications with user inputs -- naturally introducing \emph{typographical errors} (typos). Yet m…
Steering MoE LLMs via Expert (De)Activation
Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy +5
Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a fra…
Enhancing Robustness of Autoregressive Language Models against Orthographic Attacks via Pixel-based Approach
Han Yang, Jian Lan, Yihong Liu +2
Autoregressive language models are vulnerable to orthographic attacks, where input text is perturbed with characters from multilingual alphabets, leading to substantial performance…
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Sikuan Yan, Xiufeng Yang, Zuchao Huang +10
Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context win…
Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding
Qi Feng, Yihong Liu, Hinrich Schütze
Curriculum learning is a widely adopted training strategy in natural language processing (NLP), where models are exposed to examples organized by increasing difficulty to enhance l…
Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models
Shuzhou Yuan, Ercong Nie, Mario Tawfelis +3
Hate speech detection is a socially sensitive and inherently subjective task, with judgments often varying based on personal traits. While prior work has examined how socio-demogra…
LLM in the Loop: Creating the ParaDeHate Dataset for Hate Speech Detoxification
Shuzhou Yuan, Ercong Nie, Lukas Kouba +4
Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-qua…
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
Ahmad Dawar Hakimi, Ali Modarressi, Philipp Wicke +1
Understanding how large language models (LLMs) acquire and store factual knowledge is crucial for enhancing their interpretability and reliability. In this work, we analyze the evo…
XToM: Exploring the Multilingual Theory of Mind for Large Language Models
Chunkit Chan, Yauwai Yim, Hongchuan Zeng +14
Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, negle…
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma +1
Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond thes…
How Programming Concepts and Neurons Are Shared in Code Language Models
Amir Hossein Kargaran, Yihong Liu, François Yvon +1
Several studies have explored the mechanisms of large language models (LLMs) in coding tasks, but most have focused on programming languages (PLs) in a monolingual setting. In this…
Do We Know What LLMs Don't Know? A Study of Consistency in Knowledge Probing
Raoyuan Zhao, Abdullatif Köksal, Ali Modarressi +2
The reliability of large language models (LLMs) is greatly compromised by their tendency to hallucinate, underscoring the need for precise identification of knowledge gaps within L…
Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning
Yongkang Liu, Xingle Xu, Ercong Nie +5
Parameter-Efficient Fine-Tuning (PEFT) methods achieve performance comparable to Full Fine-Tuning (FFT) while requiring significantly fewer computing resources, making it the go-to…
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…
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
Ercong Nie, Helmut Schmid, Hinrich Schütze
Language confusion -- where large language models (LLMs) generate unintended languages against the user's need -- remains a critical challenge, especially for English-centric model…
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…
Through the LLM Looking Glass: A Socratic Probing of Donkeys, Elephants, and Markets
Molly Kennedy, Ayyoob Imani, Timo Spinde +2
Large Language Models (LLMs) are widely used for text generation, making it crucial to address potential bias. This study investigates ideological framing bias in LLM-generated art…