papers

Publications (21)

cs.CL2025

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…

cs.CL2024

ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks

Bolei Ma, Ercong Nie, Shuzhou Yuan +4

Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding. However, most previous studies primarily f…

cs.CL2025

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…

cs.CL2023

Cross-Lingual Constituency Parsing for Middle High German: A Delexicalized Approach

Ercong Nie, Helmut Schmid, Hinrich Schütze

Constituency parsing plays a fundamental role in advancing natural language processing (NLP) tasks. However, training an automatic syntactic analysis system for ancient languages s…

cs.CL2025

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…

cs.CL2023

Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding

Bolei Ma, Ercong Nie, Helmut Schmid +1

Multilingual pretrained language models (MPLMs) have demonstrated substantial performance improvements in zero-shot cross-lingual transfer across various natural language understan…

cs.CL2025

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…

cs.CL2025

EXECUTE: A Multilingual Benchmark for LLM Token Understanding

Lukas Edman, Helmut Schmid, Alexander Fraser

The CUTE benchmark showed that LLMs struggle with character understanding in English. We extend it to more languages with diverse scripts and writing systems, introducing EXECUTE.…

cs.CL2023

Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages

Ercong Nie, Sheng Liang, Helmut Schmid +1

Multilingual Pretrained Language Models (MPLMs) have shown their strong multilinguality in recent empirical cross-lingual transfer studies. In this paper, we propose the Prompts Au…

cs.CL2020

Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

Timo Schick, Helmut Schmid, Hinrich Schütze

A recent approach for few-shot text classification is to convert textual inputs to cloze questions that contain some form of task description, process them with a pretrained langua…

cs.CL2023

Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration

Ercong Nie, Helmut Schmid, Hinrich Schütze

Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This is…

cs.CL2024

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…

cs.CL2022

Why don't people use character-level machine translation?

Jindřich Libovický, Helmut Schmid, Alexander Fraser

We present a literature and empirical survey that critically assesses the state of the art in character-level modeling for machine translation (MT). Despite evidence in the literat…

cs.CL2025

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…

cs.CL2023

Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages

Ayyoob Imani, Peiqin Lin, Amir Hossein Kargaran +8

The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we cr…

cs.CL2024

CUTE: Measuring LLMs' Understanding of Their Tokens

Lukas Edman, Helmut Schmid, Alexander Fraser

Large Language Models (LLMs) show remarkable performance on a wide variety of tasks. Most LLMs split text into multi-character tokens and process them as atomic units without direc…

cs.CL2025

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:…

cs.CL2025

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…

cmp-lg1994

Part-of-Speech Tagging with Neural Networks

Helmut Schmid

Text corpora which are tagged with part-of-speech information are useful in many areas of linguistic research. In this paper, a new part-of-speech tagging method based on neural ne…

cs.CL2025

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…

cs.CL2025

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-…