Austria

We present SALT, a parameter-efficient approach to entity-aware machine translation that challenges the trend toward ever-larger language models. Our system combines simple SQL-based entity retrieval with a 600M parameter NLLB model, enhanced through logit biasing for knowledge integration. Despite its simplicity, SALT achieves first place in SemEval-2025 Task 2 among systems not using gold-standard data, outperforming approaches with over 100 times more parameters.
Through extensive ablations, we demonstrate that straightforward string matching rivals complex neural retrievers, single-entity candidates outperform multiple candidates, and targeted knowledge integration via logit biasing can match the performance of multi-billion-parameter LLMs. Our findings suggest that for specialized translation tasks with structured knowledge, clever integration strategies can be more effective than raw parameter scaling, achieving competitive results while remaining computationally efficient enough to run on consumer hardware.

ACL 2025

SALT at SemEval-2025 Task 2: A SQL-based Approach for LLM-Free Entity-Aware-Translation

### 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)

workshop paper

This paper presents Trans-Sent, our system developed for Track A: Multi-label Emotion Detection of SemEval-2025 Task 11: Bridging the Gap in Text-based Emotion Detection. The aim of this task is to predict the emotions that a speaker may convey i.e. perceived emotions. A target text snippet is given and our goal is to label the text by 1 and 0 as ‘yes’ and ‘no’ for different emotional classes like joy, sadness, fear, anger, surprise and/or disgust. Trans-Sent is a Transformer-based sentiment extraction model. It uses various pre-trained Bidirectional Encoder Representations from Transformers or BERT models for individual language to generate emotions and classify the emotion-labels. We have participated in the task for 7 different languages and achieve competitive results. Our system gives best result for Russian language, as it is ranked ninth among all ranked teams.

Trans-Sent at SemEval-2025 Task 11: Text-based Multi-label Emotion Detection using Pre-Trained BERT Transformer Models

We develop a system in the form of a pipeline consisting of two parts: 
Candidate Recall Module, which selects the most probable correct labels from numerous of labels based on the BERT model
LLM Prediction Module, which is used to generate the final prediction based on Large Language Models(LLM) with External Attention Module
Furthermore, with the help of data augmentation we achieve a good result


SRCB at SemEval-2025 Task 9: LLM Finetuning Approach based on External Attention Mechanism in The Food Hazard Detection

The Multilingual shared-task on Hallucinations and Related Observable Overgeneration Mistakes in the SemEval-2025 competition aims to detect hallucination spans in the outputs of instruction-tuned LLMs in a multilingual con-
text. In this paper, we address the detection of span hallucinations by applying an ensemble of approaches. In particular, we synthesized a dataset and fine-tuned LLM to detect hallucination spans. In addition, we combined this approach with a white-box method based on uncertainty quantification techniques. Using our combined pipeline, we achieved 3rd place in detecting span hallucinations in Arabic, Catalan, Finnish, Italian, and ranked within the top ten for the rest of the languages

SmurfCat at SemEval-2025 Task 3: Bridging External Knowledge and Model Uncertainty for Enhanced Hallucination Detection

This paper presents the method for the unlearning of sensitive information from
large language models as applied in the SemEval 2025 Task 4 challenge. The unlearning pipeline consists of two phases. In phase I, the model is instructed to forget specific datasets, and in phase II, the model is stabilized using a retention dataset. Unlearning with these methods secured a final score of 0.420 with the 2nd honorary mention in the 7B parameter challenge and a score of 0.36 in the 13th position for the 1B parameter challenge. The paper presents a background study, a brief literature review, and a gap analysis, as well as the methodology employed in our work titled NeuroReset. The training methodology and evaluation metrics are also presented, and the trade-offs between unlearning efficiency and model performance are discussed. The contributions of the paper are systematic unlearning, a comparative analysis of unlearning methods, and an empirical analysis of model performance post-unlearning.

NeuroReset : LLM Unlearning via Dual Phase Mixed Methodology

Hallucinations are one of the major problems of LLMs, hindering their trustworthiness and deployment to wider use cases. However, most of the research on hallucinations focuses on English data, neglecting the multilingual nature of LLMs. This paper describes our submission to the" SemEval-2025 Task-3 — Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes". We propose a two-part pipeline that combines retrieval-based fact verification against Wikipedia with a BERT-based system fine-tuned to identify common hallucination patterns. Our system achieves competitive results across all languages, reaching top-10 results in eight languages, including English. Moreover, it supports multiple languages beyond the fourteen covered by the shared task. This multilingual hallucination identifier can help to improve LLM outputs and their usefulness in the future.

TUM-MiKaNi at SemEval-2025 Task 3: Towards Multilingual and Knowledge-Aware Non-factual Hallucination Identification

The Mu-SHROOM competition in the SemEval-2025 Task 3 aims to tackle the problem of detecting spans with hallucinations in texts, generated by Large Language Models (LLMs). Our developed system, submitted to this task, is a joint architecture that utilises Named Entity Recognition (NER), Retrieval-Augmented Generation (RAG) and LLMs to gather, compare and analyse information in the texts provided by organizers. We extract entities potentially capable of containing hallucinations with NER, aggregate relevant topics for them using RAG, then verify and provide a verdict on the extracted information using the LLMs. This approach allowed with a certain level of quality to find hallucinations not only in facts, but misspellings in names and titles, which was not always accepted by human annotators in ground truth markup. We also point out some inconsistencies within annotators spans, that perhaps affected scores of all participants.

Advacheck at SemEval-2025 Task 3: Combining NER and RAG to Spot Hallucinations in LLM Answers

Understanding idioms in multimodal contexts poses significant challenges due to data scarcity, idiomatic ambiguity, and the need for effective alignment of visual and textual inputs. In this work, we introduce MIRA (Multimodal Idiom Recognition and Alignment), a training- free framework designed to address these challenges on the SemEval-2025 Task 1 (AdMIRe) benchmark. MIRA leverages powerful closed- source large language models (LLMs) and integrates three key innovations: bias correction via in-context learning, multi-step semantic- visual fusion, and a self-revision mechanism that iteratively refines its outputs through backward verification. By systematically processing and fusing multimodal inputs, MIRA generates high-quality, fine-grained image-text repre- sentations that enhance idiom comprehension across different languages and cultural contexts. Experimental evaluations in both English and Portuguese demonstrate that our approach achieves robust performance without the need for additional training, setting a new standard for multimodal idiom recognition.

PALI-NLP at SemEval 2025 Task 1: AdMIRe Advancing Multimodal Idiomaticity Representation

Question answering using Large Language Models has gained significant popularity in both everyday communication and at the workplace. However, certain tasks, such as querying tables, still pose challenges for commercial and open-source chatbots powered by advanced deep learning models. Addressing these challenges requires specialized approaches. 
During the SemEval-2025 Task 8 competition focused on tabular data, our solution achieved 86.21%accuracy and took 2nd place out of 100 teams. In this paper we present ten methods that significantly improve the baseline solution.

Samsung Research Poland at SemEval-2025 Task 8: LLM ensemble methods for QA over tabular data

Food contamination and associated illnesses represent significant global health challenges, leading to thousands of deaths worldwide. As the volume of food-related incident reports on web platforms continues to grow, there is a pressing demand for systems capable of detecting food hazards effectively. Furthermore, explainability in food risk detection is crucial for building trust in automated systems, allowing humans to validate predictions. SemEval-2025 Task 9 proposes a food hazard detection challenge to address this issue, utilizing content extracted from websites. This task is divided into two sub-tasks. Sub-task 1 involves classifying the type of hazard and product, while sub-task 2 focuses on identifying precise hazard and product ``vectors'' to offer detailed explanations for the predictions. This paper presents our participation in this task, where we introduce a transformer-based method. We fine-tune an enhanced version of the BERT transformer to process lengthy food incident reports. Additionally, we combine the transformer’s contextual embeddings to enhance its contextual representation for hazard and product ``vectors'' prediction. The experimental results reveal the competitive performance of our proposed method in this task, which achieved 7th place in both sub-tasks. We have released our code at https://github.com/AhmadMonir-CSECU/SemEval-2025_Task9.

CSECU-Learners at SemEval-2025 Task 9: Enhancing Transformer Model for Explainable Food Hazard Detection in Text

Multilingual hallucination detection stands as an underexplored challenge, which the Mu-SHROOM shared task seeks to address. In this work, we propose an efficient, training-free LLM prompting strategy that enhances detection by translating multilingual text spans into English. Our approach achieves competitive rankings across multiple languages, securing two first positions in low-resource languages.
The consistency of our results highlights the effectiveness of our translation strategy for hallucination detection, demonstrating its applicability regardless of the source language.

Downloads

Next from ACL 2025

Trans-Sent at SemEval-2025 Task 11: Text-based Multi-label Emotion Detection using Pre-Trained BERT Transformer Models

Similar lecture

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

.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

Trans-Sent at SemEval-2025 Task 11: Text-based Multi-label Emotion Detection using Pre-Trained BERT Transformer Models

Similar lecture

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

Downloads