2 citations · 13 across the 34 of their papers we have counts for
32 papers · 1 filter
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…
Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model
Rui He, Ercong Nie, Hong Jiang +3
Changes in spontaneous speech provide an early signal of cognitive dysfunction in Alzheimer's disease (AD) that large language models (LLMs) can detect. However, detection alone ca…
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…
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…
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…
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…
Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs
Shuzhou Yuan, Ercong Nie, Yinuo Sun +3
Large language models (LLMs) frequently produce false refusals, declining benign requests that contain terms resembling unsafe queries. We address this challenge by introducing two…
CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation
Shuzhou Yuan, William LaCroix, Hardik Ghoshal +2
Large Language Models (LLMs) are increasingly employed as AI tutors due to their scalability and potential for personalized instruction. However, off-the-shelf LLMs often underperf…
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…
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…
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…
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…
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…
XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs
Linyang He, Ercong Nie, Sukru Samet Dindar +10
We introduce XCOMPS in this work, a multilingual conceptual minimal pair dataset covering 17 languages. Using this dataset, we evaluate LLMs' multilingual conceptual understanding…
Language Model Re-rankers are Fooled by Lexical Similarities
Lovisa Hagström, Ercong Nie, Ruben Halifa +3
Language model (LM) re-rankers are used to refine retrieval results for retrieval-augmented generation (RAG). They are more expensive than lexical matching methods like BM25 but as…
Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence
Linyang He, Ercong Nie, Helmut Schmid +3
This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning) by distinguishing two LLM assessment paradig…
A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
Yongkang Liu, Ercong Nie, Shi Feng +5
Current state-of-the-art dialogue systems heavily rely on extensive training datasets. However, challenges arise in domains where domain-specific training datasets are insufficient…
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:…
Decoding Probing: Revealing Internal Linguistic Structures in Neural Language Models using Minimal Pairs
Linyang He, Peili Chen, Ercong Nie +2
Inspired by cognitive neuroscience studies, we introduce a novel `decoding probing' method that uses minimal pairs benchmark (BLiMP) to probe internal linguistic characteristics in…
Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models
Ercong Nie, Shuzhou Yuan, Bolei Ma +4
Probing the multilingual knowledge of linguistic structure in LLMs, often characterized as sequence labeling, faces challenges with maintaining output templates in current text-to-…
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
Shuzhou Yuan, Ercong Nie, Michael Färber +2
Large Language Models (LLMs) exhibit strong In-Context Learning (ICL) capabilities when prompts with demonstrations are used. However, fine-tuning still remains crucial to further…
Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers
Shuzhou Yuan, Ercong Nie, Bolei Ma +1
Large Language Models (LLMs) possess outstanding capabilities in addressing various natural language processing (NLP) tasks. However, the sheer size of these models poses challenge…