AACL 2025

203 papers

“The dentist is an involved parent, the bartender is not”: Revealing Implicit Biases in QA with Implicit BBQ

Aarushi Wagh, Saniya Srivastava

Between the Drafts: An Evaluation Framework for Identifying Quality Improvement and Stylistic Differences in Scientific Texts

Danqing Chen, Ingo Weber, Felix Dietrich

Fair Play in the Newsroom: Actor-Based Filtering Gender Discrimination in Text Corpora

Stefanie Urchs, Veronika Thurner, Matthias Aßenmacher, Christian Heumann, Stephanie Thiemichen

Reliable Inline Code Documentation with LLMs: Fine-Grained Evaluation of Comment Quality and Coverage

Rohan Patil, Gaurav Tirodkar, Shubham Gatfane

Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation

Naila Shafirni Hidayat, Muhammad Dehan Al Kautsar, Alfan Farizki Wicaksono, Fajri Koto

Measuring Visual Understanding in Telecom domain: Performance Metrics for Image-to-UML conversion using VLMs

H. G. Ranjani, Rutuja Prabhudesai

Beyond Tokens and Into Minds: Future Directions for Human-Centered Evaluation in Machine Translation Post-Editing

Molly Apsel, Sunil Kothari, Manish Mehta, Vasudevan Sundarababu

“AGI” team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTa

Harsh Rathwa, Pruthwik Mishra, Shrikant Malviya

Scalar_NITK at SHROOM-CAP: Multilingual Factual Hallucination and Fluency Error Detection in Scientific Publications Using Retrieval-Guided Evidence and Attention-Based Feature Fusion

Anjali R

SmurfCat at SHROOM-CAP: Factual but Awkward? Fluent but Wrong? Tackling Both in LLM Scientific QA

Timur Ionov, Evgenii Nikolaev, Artem Vazhentsev, Mikhail Chaichuk, Anton Korznikov

SHROOM-CAP: Shared Task on Hallucinations and Related Observable Overgeneration Mistakes in Crosslingual Analyses of Publications

Aman Sinha, Federica Gamba, Raúl Vázquez, Timothee Mickus, Ahana Chattopadhyay

A Comprehensive Evaluation of Large Language Models for Retrieval-Augmented Generation under Noisy Conditions

Josue Caldas, Elvis de Souza

Language Confusion and Multilingual Performance: A Case Study of Thai-Adapted Large Language Models

Pakhapoom Sarapat, Trapoom Ukarapol, Tatsunori Hashimoto

Leveraging NTPs for Efficient Hallucination Detection in VLMs

Ofir Azachi, Kfir Eliyahu, Eyal El Ani, Rom Himelstein, Roi Reichart

Better Together: Towards Localizing Fact-Related Hallucinations using Open Small Language Models

David Kletz, Sandra Mitrović, Ljiljana Dolamic, Fabio Rinaldi

Examining the Faithfulness of Deepseek R1’s Chain-of-Thought Reasoning

Chrisanna Cornish, Anna Rogers

Task-Aware Evaluation and Error-Overlap Analysis for Large Language Models

Pranava Madhyastha

Team Horizon at BHASHA Task 2: Fine-tuning Multilingual Transformers for Indic Word Grouping

Manav Dhamecha, Gaurav Damor, Sunil Jaat, Pruthwik Mishra

akhilrajeevp at BHASHA Task 1: Minimal-Edit Instruction Tuning for Low-Resource Indic GEC

Akhil Rajeev P

DLRG at BHASHA: Task 1 (IndicGEC): A Hybrid Neurosymbolic Approach for Tamil and Malayalam Grammatical Error Correction

Akshay Ramesh, Ratnavel Rajalakshmi

A3-108 at BHASHA Task1: Asymmetric BPE configuration for Grammar Error Correction

Saumitra Yadav, Manish Shrivastava

Team Horizon at BHASHA Task 1: Multilingual IndicGEC with Transformer-based Grammatical Error Correction Models

Manav Dhamecha, Sunil Jaat, Gaurav Damor, Pruthwik Mishra

Niyamika at BHASHA Task 1: Word-Level Transliteration for English-Hindi Mixed Text in Grammar Correction Using MT5

Rucha Ambaliya, Mahika Dugar, Pruthwik Mishra

Findings of the IndicGEC and IndicWG Shared Task at BHASHA 2025

Pramit Bhattacharyya, Karthika N J, Hrishikesh Terdalkar, Manoj Balaji Jagadeeshan, Shubham Kumar Nigam

Accent Placement Models for Rigvedic Sanskrit Text

Akhil Rajeev P, Annarao Kulkarni

Mātṛkā: Multilingual Jailbreak Evaluation of Open-Source Large Language Models

Murali Emani, Kashyap Manjusha R

BHRAM-IL: A Benchmark for Hallucination Recognition and Assessment in Multiple Indian Languages

Hrishikesh Terdalkar, Kirtan Bhojani, Aryan Dongare, Omm Aditya Behera

AnciDev: A Dataset for High-Accuracy Handwritten Text Recognition of Ancient Devanagari Manuscripts

Vriti Sharma, Rajat Verma, Rohit Saluja

Automatic Accent Restoration in Vedic Sanskrit with Neural Language Models

Yuzuki Tsukagoshi, Ikki Ohmukai

Aligning Large Language Models to Low-Resource Languages through LLM-Based Selective Translation: A Systematic Study

Rakesh Paul, Anusha Kamath, Kanishk Singla, Raviraj Joshi, Utkarsh Vaidya

Benchmarking Hindi LLMs: A New Suite of Datasets and a Comparative Analysis

Anusha Kamath, Kanishk Singla, Rakesh Paul, Raviraj Bhuminand Joshi, Utkarsh Vaidya

INDRA: Iterative Difficulty Refinement Attention for MCQ Difficulty Estimation for Indic Languages

Manikandan Ravikiran, Rohit Saluja, Arnav Bhavsar

Auditing Political Bias in Text Generation by GPT-4 using Sociocultural and Demographic Personas: Case of Bengali Ethnolinguistic Communities

Dipto Das, Syed Ishtiaque Ahmed, Shion Guha

Indian Grammatical Tradition-Inspired Universal Semantic Representation Bank (USR Bank 1.0)

Soma Paul, Sukhada Sukhada, Bidisha Bhattacharjee, Kumari Riya, Sashank Tatavolu

Multi-Feature Graph Convolution Network for Hindi OCR Verification

Shikhar Dubey, Krish Mittal, Sourava Kumar Behera, Manikandan Ravikiran, Nitin Kumar

Code_Gen at BLP-2025 Task 2: BanglaCode: A Cross-lingual Benchmark for Code Generation with Translation and Assertion Strategies

Abhishek Agarwala, Shifat Islam, Emon Ghosh

BRACU_CL at BLP-2025 Task 2: CodeMist: A Transformer-Based Framework for Bangla Instruction-to-Code Generation

Md. Fahmid-Ul-Alam Juboraj, Soumik Deb Niloy, Mahbub E Sobhani, Farig Sadeque

TeamB2B at BLP-2025 Task 2: BanglaForge: LLM Collaboration with Self-Refinement for Bangla Code Generation

Mahir Labib Dihan, Sadif Ahmed, Md Nafiu Rahman

AdversaryAI at BLP-2025 Task 2: A Think, Refine, and Generate (TriGen) System with LoRA and Self-Refinement for Code Generation

Omar Faruqe Riyad, Jahedul Alam Junaed

PyBhasha at BLP-2025 Task 2: Effectiveness of Semantic-Aware Translation and Ensembling in Bangla Code Generation

Foyez Ahmed Dewan, Nahid Montasir Rifat

AlphaBorno at BLP-2025 Task 2: Code Generation with Structured Prompts and Execution Feedback

Mohammad Ashfaq Ur Rahman, Muhtasim Ibteda Shochcho, Md Fahim

CUET_Expelliarmus at BLP2025 Task 2: Leveraging Instruction Translation and Refinement for Bangla-to-Python Code Generation with Open-Source LLMs

Md Kaf Shahrier, Suhana Binta Rashid, Hasan Mesbaul Ali Taher, Mohammed Moshiul Hoque

NALA_MAINZ at BLP-2025 Task 2: A Multi-agent Approach for Bengali Instruction to Python Code Generation

Hossain Shaikh Saadi, Faria Alam, Mario Sanz-Guerrero, Minh Duc Bui, Manuel Mager

NSU_PiedPiper at BLP-2025 Task 2: A Chain-of-Thought with Iterative Debugging Approach for Code Generation with Bangla Instruction

Ahmad Fahmid, Fahim Foysal, Wasif Haider, Shafin Rahman, Md Adnan Arefeen

Retriv at BLP-2025 Task 2: Test-Driven Feedback-Guided Framework for Bangla-to-Python Code Generation

K M Nafi Asib, Sourav Saha, Mohammed Moshiul Hoque

JU_NLP at BLP-2025 Task 2: Leveraging Zero-Shot Prompting for Bangla Natural Language to Python Code Generation

Pritam Pal, Dipankar Das

Musafir at BLP_2025 Task 2: Generating Python Code from Bangla Prompts using a Multi Model Cascade and Unit Test Validation

Sakibul Hasan, Md Tasin Abdullah, Abdullah Al Mahmud, Ayesha Banu

Barrier Breakers at BLP-2025 Task 2: Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter

Sajed Jalil, Shuvo Saha, Hossain Mohammad Seym

PyBangla at BLP-2025 Task 2: Enhancing Bangla-to-Python Code Generation with Iterative Self-Correction and Multilingual Agents

Jahidul Islam, Md Ataullha, Saiful Azad

Troopers at BLP-2025 Task 2: Reward-Selective Fine-Tuning based Code Generation Approach for Bangla Prompts

Musa Tur Farazi, Nufayer Jahan Reza

CodeAnubad at BLP-2025 Task 2: Efficient Bangla-to-Python Code Generation via Iterative LoRA Fine-Tuning of Gemma-2

Soumyajit Roy

Ecstasy at BLP-2025 Task 1: TF-IDF Informed Prompt Engineering with LoRA Fine-tuning for Bangla Hate Speech Detection

Kazi Reyazul Hasan, Mubasshira Musarrat, Muhammad Abdullah Adnan

HateNet-BN at BLP-2025 Task 1: A Hierarchical Attention Approach for Bangla Hate Speech Detection

Mohaymen Ul Anam, Akm Moshiur Rahman Mazumder, Ashraful Islam, Akmmahbubur Rahman, M Ashraful Amin

PentaML at BLP-2025 Task 1: Linear Probing of Pre-trained Transformer-based Models for Bangla Hate Speech Detection

Intesar Tahmid, Rafid Ahmed, Md Mahir Jawad, Anam Borhan Uddin, Md Fahim

Velora at BLP-2025 Task 1: Multi-Method Evaluation for Hate Speech Classification in Bangla Text

Sad Yeamin Sayem, Sabira Rahman

CUET_Sntx_Srfrs at BLP-2025 Task 1: Combining Hierarchical Classification and Ensemble Learning for Bengali Hate Speech Detection

Hafsa Hoque Tripty, Laiba Tabassum, Hasan Mesbaul Ali Taher, Kawsar Ahmed, Mohammed Moshiul Hoque

Code_Gen at BLP-2025 Task 1: Enhancing Bangla Hate Speech Detection with Transformers through Token-Aware Adversarial Contrastive Training and Layer-wise Learning Rate Decay

Shifat Islam, Abhishek Agarwala, Emon Ghosh

SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection

Md. Shihab Uddin Riad

PerceptionLab at BLP-2025 Task 1: Domain-Adapted BERT for Bangla Hate Speech Detection: Contrasting Single-Shot and Hierarchical Multiclass Classification

Tamjid Hasan Fahim, Kaif Ahmed Khan

CoU-CU-DSG at BLP-2025 Task 1: Leveraging Weighted Probabilistic Fusion of Language Models for Bangla Hate Speech Detection

Ashraful Alam, Abdul Aziz, Abu Nowshed Chy

Retriv at BLP-2025 Task 1: A Transformer Ensemble and Multi-Task Learning Approach for Bangla Hate Speech Identification

Sourav Saha, K M Nafi Asib, Mohammed Moshiul Hoque

Heisenberg at BLP-2025 Task 1: Bangla Hate Speech Classification using Pretrained Language Models and Data Augmentation

Samin Yasir

Catalyst at BLP-2025 Task 1: Transformer Ensembles and Multi-task Learning Approaches for Bangla Hate Speech Detection

Nahid Hasan

NSU_MILab at BLP-2025 Task 1: Decoding Bangla Hate Speech: Fine-Grained Type and Target Detection via Transformer Ensembles

Md. Mohibur Rahman Nabil, Muhammad Rafsan Kabir, Rakib Islam, Fuad Rahman, Nabeel Mohammed

TeamHateMate at BLP Task1: Divide and Conquer: A Two-Stage Cascaded Framework with K-Fold Ensembling for Multi-Label Bangla Hate Speech Classification

Mahbub Islam Mahim, Mehedi Hasan

CUET-NLP_Zenith at BLP-2025 Task 1: A Multi-Task Ensemble Approach for Detecting Hate Speech in Bengali YouTube Comments

Md. Refaj Hossan, Kawsar Ahmed, Mohammed Moshiul Hoque

Computational Story Lab at BLP-2025 Task 1: HateSense: A Multi-Task Learning Framework for Comprehensive Hate Speech Identification using LLMs

Tabia Tanzin Prama, Christopher M. Danforth, Peter Dodds

BElite at BLP-2025 Task 1: Leveraging Ensemble for Multi Task Hate Speech Detection in Bangla

Zannatul Fardaush Tripty, Ibnul Mohammad Adib, Nafiz Fahad, Muhammad Tanjib Hussain, Md Kishor Morol

PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection

Rakib Hossan, Shubhashis Roy Dipta

Gradient Masters at BLP-2025 Task 1: Advancing Low-Resource NLP for Bengali using Ensemble-Based Adversarial Training for Hate Speech Detection

Syed Mohaiminul Hoque, Naimur Rahman, Md Sakhawat Hossain

Bahash-AI at BLP-2025 Task 1: Bangla Hate Speech Detection using Data Augmentation and Pre-trained Model

Sahinur Rahman Laskar, Bishwaraj Paul

Overview of BLP-2025 Task 1: Bangla Hate Speech Identification

Md Arid Hasan, Firoj Alam, Md Fahad Hossain, Usman Naseem, Syed Ishtiaque Ahmed

Overview of BLP-2025 Task 2: Code Generation in Bangla

Nishat Raihan, Mohammad Anas Jawad, Md Mezbaur Rahman, Noshin Ulfat, Pranav Gupta

Form-aware Poetic Generation for Bangla

Amina, Abdullah, Mueeze Al Mushabbir, Sabbir Ahmed

bnContextQA: Benchmarking Long-Context Question Answering and Challenges in Bangla

Adnan Ahmad, Labiba Adiba, Namirah Rasul, Md Tahmid Rahman Laskar, Sabbir Ahmed

Generative Data Augmentation for Improving Semantic Classification

Shadman Rohan, Mahmud Elahi Akhter, Ibraheem Muhammad Moosa, Nabeel Mohammed, Amin Ahsan Ali

Robustness of LLMs to Transliteration Perturbations in Bangla

Fabiha Haider, Md Farhan Ishmam, Fariha Tanjim Shifat, Md Tasmim Rahman Adib, Md Fahim

Benchmarking Large Language Models on Bangla Dialect Translation and Dialectal Sentiment Analysis

Md Mahir Jawad, Rafid Ahmed, Ishita Sur Apan, Tasnimul Hossain Tomal, Fabiha Haider

Clustering LLM-based Word Embeddings to Determine Topics from Bangla Articles

Rifat Rahman, Mohammed Eunus Ali

LLMs for Low-Resource Dialect Translation Using Context-Aware Prompting: A Case Study on Sylheti

Tabia Tanzin Prama

Exploring Cross-Lingual Knowledge Transfer via Transliteration-Based MLM Fine-Tuning for Critically Low-resource Chakma Language

Adity Khisa, Nusrat Jahan Lia, Tasnim Mahfuz Nafis, Zarif Masud, Tanzir Pial

A Comparative Analysis of Retrieval-Augmented Generation Techniques for Bengali Standard-to-Dialect Machine Translation Using LLMs

K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque

ChakmaBridge: A Five-Way Parallel Corpus for Navigating the Script Divide in an Endangered Language

Md. Abdur Rahman, Md. Tofael Ahmed Bhuiyan, Abdul Kadar Muhammad Masum

BOIGENRE: A Large-Scale Bangla Dataset for Genre Classification from Book Summaries

Rafi Hassan Chowdhury, Rahanuma Ryaan Ferdous

BanHate: An Up-to-Date and Fine-Grained Bangla Hate Speech Dataset

Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Tahmid Hasan Fuad, Md Farhan Ishmam, Md Fahim

Human–LLM Benchmarks for Bangla Dialect Translation: Sylheti and Chittagonian on the BanglaCHQ-Summ Corpus

Nowshin Mahjabin, Ahmed Shafin Ruhan, Mehreen Chowdhury, Md Fahim, Md Azam Hossain

LP-FT-LoRA: A Three-Stage PEFT Framework for Efficient Domain Adaptation in Bangla NLP Tasks

Tasnimul Hossain Tomal, Anam Borhan Uddin, Intesar Tahmid, Mir Sazzat Hossain, Md Fahim

P6Jiggasha: Benchmarking Large Language Models on Bangla Physics Question Answering with Cross-lingual Evaluation

S.m. Shahriar, Md Tahmid Hasan Fuad, Md Fahim, Md. Azad Hossain

BanHateME : Understanding Hate in Bangla Memes thorough Detection, Categorization, and Target Profiling

Md Ayon Mia, Md Fahim

BLUCK: A Benchmark Dataset for Bengali Linguistic Understanding and Cultural Knowledge

Daeen Kabir, Minhajur Rahman Chowdhury Mahim, Sheikh Shafayat, Adnan Sadik, Arian Ahmed

A Comprehensive Text Optimization Approach to Bangla Summarization

Irtifa Haider, Shanjida Alam, Md. Tazel Hossan, Md. Musfique Anwar, Tanjim Taharat Aurpa

Gen-mABSA-T5: A Multilingual Zero-Shot Generative Framework for Aspect-Based Sentiment Analysis

Shabrina Akter Shahana, Nuzhat Nairy Afrin, Md Musfique Anwar, Israt Jahan

Advancing Subjectivity Detection in Bengali News Articles Using Transformer Models with POS-Aware Features

Md Minhazul Kabir, Kawsar Ahmed, Mohammad Ashfak Habib, Mohammed Moshiul Hoque

CheckSent-BN: A Bengali Multi-Task Dataset for Claim Checkworthiness and Sentiment Classification from News Headlines

Pritam Pal, Dipankar Das

BhasaBodh: Bridging Bangla Dialects and Romanized Forms through Machine Translation

Md. Tofael Ahmed Bhuiyan, Md. Abdur Rahman, Abdul Kadar Muhammad Masum

A Hybrid Transformer–Sequential Model for Depression Detection in Bangla–English Code-Mixed Text

Md Siddikul Imam Kawser, Jidan Al Abrar, Mehebub Bin Kabir, Md. Rayhan Chowdhury, Md Ataullah Bahari

Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders

Souvika Sarkar, Md Najib Hasan, Santu Karmaker

BiCap: Bangla Image Captioning Using Attention-based Encoder-Decoder Architecture

Md Aminul Kader Bulbul

Read Between the Lines: A Benchmark for Uncovering Political Bias in Bangla News Articles

Nusrat Jahan Lia, Shubhashis Roy Dipta, Abdullah Khan Zehady, Naymul Islam, Madhusodan Chakraborty

BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects

Jakir Hasan, Shubhashis Roy Dipta