Austria

The Unlearning Sensitive Content from Large Language Models task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradientbased unlearning using low-rank (LoRA) adaptation and layer-focused fine-tuning. To further enhance unlearning effectiveness, we employ data chunking, splitting forget data into disjoint
partitions and merging them with cyclically sampled retain samples at a pre-defined
ratio. Our task-agnostic method achieves an outstanding forget-retain balance, ranking first on leaderboards and significantly outperforming baselines and competing systems.

ACL 2025

AILS-NTUA at SemEval-2025 Task 4: Parameter-Efficient Unlearning for Large Language Models using Data Chunking

## Welcome!
"I am excited to welcome you to this year’s edition of the Conference on Empirical Methods in Natural Language Processing! Importantly, it marks the 30th edition of EMNLP. With over 8,000 submissions, more than 3,000 accepted papers, and thousands of attendees, we have come a long way from that first
workshop, which had 14 accepted papers. As the field looks ahead, Suzhou is the fitting location for celebrating this milestone: rooted in a long literary tradition, yet modern and forward-looking, and home to a large share of the NLP community." 

*Message from the General Chair, Dirk Hovy*

EMNLP 2025

Celebrate 30 Years of EMNLP! 
EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025.

workshop paper

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

This study introduces a methodology centred
on Llama 3 fine-tuning for the classification of
entities mentioned within news articles, based
on a predefined role taxonomy. The research
is conducted as part of SemEval-2025 Task 10,
which focuses on the automatic identification
of narratives, their classification, and the deter-
mination of the roles of the relevant entities in-
volved. The developed system was specifically
used within Subtask 1 on Entity Framing. The
approach used is based on parameter-efficient
fine-tuning, in order to minimize the computa-
tional costs while maintaining reasonably good
model performance across all datasets and lan-
guages involved. The model achieved promis-
ing results on both the development and test
sets. Specifically, during the final evaluation
phase, it attained an average accuracy of 0.84
on the main role and an average Exact Match
Ratio of 0.41 in the prediction of fine-grained
roles across all the five languages involved, i.e.
Bulgarian, English, Hindi, Portuguese and Rus-
sian. The best performance was observed for
English (3rd place out of 32 participants), on
a par with Hindi and Russian. The paper pro-
vides an overview of the system adopted for the
task and discusses the results obtained.

DEMON at SemEval-2025 Task 10: Fine-tuning LLaMA-3 for Multilingual Entity Framing

Idioms and figurative language are nuanced linguistic phenomena that transport semanticity and culture via non-compositional multi-word expressions. This type of figurative language remains difficult for small and large language models to handle. For language models to become more valuable as translators and even companions, natural language must be understood and generated. A portion of this is idiomatic and figurative language. Various attempts have been made to identify idiomaticity in text. The approach presented in this paper represents an intuitive attempt to accurately address Task 1: AdMIRe Subtask A to correctly order a series of images and captions by concatenating the image captions as a sequence. The methods employ the reliability of a pre-trained vision and language model for the image-type task and a large language model with instruction fine-tuning for a causal language model approach to handle the caption portion of the task. The models chosen for development in the pipeline were based on their respective reliability in captioning and instruction fine-tuning.

JNLP at SemEval-2025 Task 1: Multimodal Idiomaticity Representation with Large Language Models

This paper describes the machine translation system submitted to the SemEval-2025 Entity-Aware Machine Translation Task by the SheffieldGATE Team. We proposed a multi-agent entity-aware machine translation system that operates through three distinct reasoning stages: entity recognition, knowledge enhancement, and translation decision-making. The innovation in our approach lies in leveraging large language models to generate contextually relevant queries during the knowledge enhancement stage, extracting candidate entities and their translations from external knowledge bases. In the final translation decision-making stage, we employ fine-tuned large language models to denoise the retrieved knowledge, selecting the most relevant entity information to ensure accurate translation of the original text. Experimental results demonstrate our system's effectiveness. In SemEval-2025 Task 2, our system ranks first among all systems in Spanish entity translation metrics and third in Italian. For systems that do not use gold standard entity IDs during test set inference, ours achieves the highest overall scores across four language pairs: German, French, Italian, and Spanish.

SheffieldGATE at SemEval-2025 Task 2: Multi-Stage Reasoning with Knowledge Fusion for Entity Translation

This paper presents our system for SemEval-
2025 Task 8: DataBench, Question-Answering
over Tabular Data. The primary objective of
this task is to perform question answering on
given tabular datasets from diverse domains un-
der two subtasks: DataBench QA (Subtask I)
and DataBench Lite QA (Subtask II). To tackle
both subtasks, we developed a zero-shot solu-
tion with a particular emphasis on leveraging
Large Language Model (LLM)-based code gen-
eration. Specifically, we propose a Python code
generation framework utilizing state-of-the-art
open-source LLMs to generate executable Pan-
das code via optimized prompting strategies.
Our experiments reveal that different LLMs ex-
hibit varying levels of effectiveness in Python
code generation. Additionally, results show
that Python code generation achieves supe-
rior performance in tabular question answering
compared to alternative approaches. Although
our ranking among zero-shot systems is un-
known at the time of this paper’s submission,
our system achieved eighth place in Subtask
I and sixth place in Subtask II among the 30
systems that outperformed the baseline in the
open-source models category.

ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation

Food safety is a critical global concern, and automating the detection of food hazards from recall reports can improve public health monitoring and regulatory compliance. This paper presents our submission for SemEval-2025 Task 9: The Food Hazard Detection Challenge. We tackle the inherent class imbalance in this task by leveraging advanced data augmentation techniques, including LLM-based synthetic data generation, synonym replacement, and back-translation. We employ transformer-based models such as DistilBERT, fine-tuned with these augmented datasets, to enhance performance. Our system achieves significant improvements, obtaining a Macro-F1 score of 0.7882 in ST1 and 0.5099 in ST2. Additionally, we analyze the impact of augmentation strategies and compare multiple architectures, highlighting challenges in handling implicit hazards. Our findings underscore the effectiveness of LLM-based augmentation in addressing extreme class imbalance while demonstrating the strengths and limitations of transformer models in food safety applications.

HU at SemEval-2025 Task 9: Leveraging LLM-Based Data Augmentation for Class Imbalance

The focus of SemEval-2024 Task 7 is the retrieval of relevant fact-checks for social media posts across multiple languages. We approach this task with an enhanced bi-encoder retrieval setup, which is designed to match social media posts with relevant fact-checks using synthetic data from LLMs.We explored and analyzed two main approaches for generating synthetic posts.Either based on existing fact-checks or on existing posts.Our approach achieved an S@10 score of 89.53% for the monolingual task and 74.48% for the crosslingual task, ranking 16th out of 28 and 13th out of 29, respectively. Without data augmentation, scores would have been 88.69 (17th) and 72.93 (15th).

CAIDAS at SemEval-2025 Task 7: Enriching Sparse Datasets with LLM-Generated Content for Improved Information Retrieval

Harmful disinformation and propaganda proliferate at unprecedented rates, highlighting the need for effective detection and analysis methods. Identifying and analyzing manipulative narratives in online news is critical to mitigate their impact on public opinion. This paper addresses SemEval-2025 Task 10 on “Multilingual Characterization and Extraction of Narratives from Online News” Piskorski et al. (2025) by focusing on three subtasks that revolve around classifying entities, categorizing news articles into narratives and subnarratives, and generating concise summaries for a given article.
We have employed various deep learning techniques in multilingual settings to tackle these challenges. Our results demonstrate the effectiveness of BART-based models in capturing the framing context of entities and generating narrative-focused summaries, ultimately offering insights into the dynamics of online narratives and contributing to efforts against harmful disinformation.

NarrativeMiners at SemEval-2025 Task 10: Combating Manipulative Narratives in Online News

Question Answering over large tables is challenging due to the difficulty of reasoning required in linking information from different parts of a table, such as heading and metadata to the values in the table. We investigate using Large Language Models (LLM) for tabular reasoning, where, given a pair of a table and a question from the DataBench benchmark, the models generate answers. We experiment with three techniques that enable symbolic reasoning through code execution: (1) a direct code prompting (DCP) approach that uses Python; (2) Multi-Step Code (MSC) prompting using SQL and ReAct prompting; and (3) a combination of multi-step reasoning (MSR), few-shot (FS) learning, and Python tools. We also conduct an analysis exploring the impact of answer types, data size, and multi-column dependencies on LLMs' answer generation performance, including an assessment of the models' limitations and the underlying challenges of tabular reasoning in LLMs.


CSIRO LT at SemEval-2025 Task 8: Answering Questions over Tabular Data using LLMs

We present our approach to SemEval-2025 Task 6 (PromiseEval), which focuses on verifying promises in corporate ESG reports across four subtasks: identification, evidence assessment, clarity evaluation, and timing \cite{chen2025semeval}. We explore three models: (1) ESG-BERT \cite{mukherjee2021esgbert} with task-specific heads, (2) an enhanced version with subtask-specific linguistic features, and (3) a unified model combining attention-based pooling, document metadata, and multi-objective learning. On the English ML-Promise dataset, our unified model achieves a score of 0.5268, outperforming the baseline (0.5227), demonstrating the benefits of linguistic features, attention mechanisms, and multi-objective training despite challenges like class imbalance and limited data.

CLaC at SemEval-2025 Task 6: A Multi-Architecture Approach for Corporate Environmental Promise Verification

This paper presents our participation in the SemEval-2025 task 6: multinational, multilingual, multi-industry promise verification. The SemEval-2025 Task 6 aims to extract Promise Identification, Supporting Evidence, Clarity of the Promise-Evidence Pair, and Timing for Verification from the promises made to businesses and governments. Using these data to verify whether companies and governments have fulfilled their promises. In this task, we focus on the English dataset. Our model introduces regularization dropout based on the BERT-base model to focus on the stability of non-targe classes, improve the robustness of the model, and ultimately improve the indicators. Our approach obtained competitive results in task.

Downloads

Next from ACL 2025

DEMON at SemEval-2025 Task 10: Fine-tuning LLaMA-3 for Multilingual Entity Framing

Similar lecture

SEPS: A Separability Measure for Robust Unlearning in LLMs

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ACL 2025

DEMON at SemEval-2025 Task 10: Fine-tuning LLaMA-3 for Multilingual Entity Framing

Similar lecture

SEPS: A Separability Measure for Robust Unlearning in LLMs

Downloads