Papers by Helmut Schmid

13 papers
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit strong In-Context Learning (ICL) capabilities when prompts with demonstrations are used.
Approach: They propose a prompt-based parameter-efficient fine-tuning approach that leverages insights into ICL’s information flow dynamics and hardwires the desired information flow into the GNN.
Outcome: The proposed approach surpasses prompt-based fine-tuning methods in few-shot settings by updating just 0.2% to 0.5% of parameters.
Cross-Lingual Retrieval Augmented Prompt for Low-Resource Languages (2023.findings-acl)

Copied to clipboard

Challenge: Multilingual pretrained language models (MPLMs) perform strongly in cross-lingual transfer.
Approach: They propose to augment context with similar sentences retrieved from a high-resource language (HRL) they find a significant correlation between cross-lingual transfer performance and similarity between high- and low-resourced languages .
Outcome: The proposed model outperforms finetuning by 3.7% on three downstream tasks with multilingual parallel test sets across 10 LRLs covering 6 language families in unlabeled and labeled settings.
Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluations of Large Language Models (LLMs) reflect statistical rules that may not accurately represent LLMs’ true linguistic competence.
Approach: They propose a method that combines minimal pair and diagnostic probing to analyze activation patterns across model layers.
Outcome: The proposed method combines minimal pair and diagnostic probing to analyze activation patterns across model layers.
Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent research demonstrates that multilingual encoder models are capable of zero-shot cross-lingual learning by using cloze-style prompts.
Approach: They propose to reformulate input examples into cloze-style prompts to perform zero-shot multilingual tasks or linguistic probing by predicting label words at the masked token position.
Outcome: The proposed method performs zero-shot multilingual tasks without updating parameters.
CUTE: Measuring LLMs’ Understanding of Their Tokens (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) perform well on a wide variety of tasks, authors say . they lack direct access to characters, which can be difficult to generalize to new languages .
Approach: They propose a benchmark to test the orthographic knowledge of Large Language Models . they find that most LLMs seem to know the spelling of their tokens - yet fail to manipulate text .
Outcome: The proposed benchmark tests the orthographic knowledge of large language models . it finds that most LLMs seem to know the spelling of their tokens, but fail to manipulate text .
Why don’t people use character-level machine translation? (2022.findings-acl)

Copied to clipboard

Challenge: despite evidence character-level systems are comparable with subword systems, they are rarely used in competitive setups in machine translation competitions.
Approach: They propose a two-step decoder architecture that does not suffer from a slow-down due to the length of character sequences.
Outcome: The proposed character-level MT systems show better domain robustness and better morphological generalization . the proposed decoder architecture shows no slow-down due to the length of character sequences .
XToM: Exploring the Multilingual Theory of Mind for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations of ToM in LLMs are limited to English, neglecting the linguistic diversity that shapes human cognition.
Approach: They propose a multilingual benchmark that evaluates ToM across five languages . they find that models excel in multilingual language understanding, but their ToM performance varies across languages.
Outcome: The proposed benchmark evaluates LLMs across five languages and incorporates diverse task scenarios.
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning (2025.acl-long)

Copied to clipboard

Challenge: Using a benchmark for cross-lingual knowledge editing, knowledge editing is underexplored.
Approach: They propose a benchmark for cross-lingual in-context knowledge editing that spans 53 languages and three KE datasets.
Outcome: The proposed benchmark systematically evaluates cross-lingual knowledge editing (IKE) under zero-shot, one-shot and few-shot setups.
EXECUTE: A Multilingual Benchmark for LLM Token Understanding (2025.findings-acl)

Copied to clipboard

Challenge: EXECUTE is an expandable X(Cross)-Lingual Extension of CUTE that can be expanded to any language.
Approach: They extend the CUTE benchmark to more languages with diverse scripts and writing systems, introducing EXECUTE.
Outcome: The extended framework allows expansion to any language.
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Language confusion is a critical challenge for large language models, especially for English-centric models.
Approach: They propose to combine behavioral benchmarking with neuron-level analysis to study language confusion.
Outcome: The proposed approach matches multilingual alignment in confusion reduction for many languages and yields cleaner, higher-quality outputs.
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages (2023.acl-long)

Copied to clipboard

Challenge: Lack of LLMs supporting low-resource languages is a serious impediment to bringing NLP to all of the world.
Approach: They create a model that scales LLMs horizontally and a corpus that covers 511 low-resource languages.
Outcome: The proposed model improves on five diverse tasks across low- and high-resource languages.
Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to few-shot text classification require domain expertise and an understanding of the language model's abilities to define the mapping between words and labels.
Approach: They propose a method that converts textual inputs to cloze questions that contain some form of task description and processes them with a pretrained language model to map the predicted words to labels.
Outcome: The proposed approach performs almost as well as hand-crafted label-to-word mappings for a number of tasks with small amounts of training data.
ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks (2024.eacl-long)

Copied to clipboard

Challenge: Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding.
Approach: They propose a prompt-based method for token-level sequence labeling tasks . they propose to decompose an input sentence into single tokens and apply one prompt template to each token.
Outcome: The proposed method outperforms Vanilla fine-tuning and Prompt-Tuning in zero-shot cross-lingual transfer . the method also attains state-of-the-art performance when employed with the mT5 model .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations