Publications

Research Areas

LLM Inference / Reasoning LLM as Judge for Evaluation Reinforcement Learning for Alignment / Reasoning Multimodal Learning Social NLP

* Denotes Equal Contribution

Preprints

  1. Under Review
    Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?
    Eftekhar Hossain, Santu Karmaker
    arxiv
  2. Under Review
    The Critical Role of Aspects in Evaluating Document Similarity
    Eftekhar Hossain, Tarnika Hazra, Ahatesham Bhuiyan, Santu Karmaker
    arxiv

2026

  1. NeurIPS Evaluation Track
    Evaluating Whether LLMs Can Reliably Connect the DOTs?
    Eftekhar Hossain, John Salvador, Santu Karmaker
    NeurIPS Evaluation Track, 2026
    Paper Code
  2. AACL Findings
    Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design
    Omar Sharif, Eftekhar Hossain, Nikhil Singh, Patrick Ng
    AACL Findings, 2026
    Paper

2025

  1. ACL
    FIHA: Automated Fine-grained Hallucinations Evaluations in Large Vision Language Models with Davidson Scene Graphs
    Bowen Yan, Zhengsong Zhang, Liqiang Jing, Eftekhar Hossain, Xinya Du
    In Proc. of ACL Findings, 2025
    Paper Code
  2. ACL
    BenNumEval: A Benchmark to Assess LLMs’ Numerical Reasoning Capabilities in Bengali
    Kawsar Ahmed, Md Osama, Omar Sharif, Eftekhar Hossain, Mohammed Moshiul Hoque
    In Proc. of ACL Findings, 2025
    Paper Code
  3. NAACL
    LLMs as Meta-Reviewers’ Assistants: A Case Study
    Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal, Santu Karmaker et al.
    In Proc. of NAACL Main, 2025
    Paper Code

2024

  1. ACL
    Deciphering Hate: Identifying Hateful Memes and Their Targets
    Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque, and Sarah Masud Preum
    In Proc. of ACL Main, 2024
    Paper Code
  2. EACL
    A Multimodal Framework to Detect Target Aware Aggression in Memes
    Shawly Ahsan*, Eftekhar Hossain*, Omar Sharif, Avishek Das, Mohammed Moshiul Hoque, M. Dewan
    In Proc. of EACL Main, 2024
    Paper Code
  3. EACL
    Align before Attend: Aligning Visual and Textual Features for Multimodal Hateful Content Detection
    Eftekhar Hossain*, Omar Sharif*, Mohammed Moshiul Hoque, and Sarah Masud Preum
    In Proc. of EACL, Student Research Workshop (SRW), 2024
    Paper Code

2022

  1. AACL
    MUTE: A Multimodal Dataset for Detecting Hateful Memes
    Eftekhar Hossain, Omar Sharif, and Mohammed Moshiul Hoque
    In Proc. of AACL, Student Research Workshop (SRW), 2022
    Paper Code
  2. Journal
    Identification of Multilingual Offense and Troll from Social Media Memes Using Weighted Ensemble of Multimodal Features
    Eftekhar Hossain, Omar Sharif, Mohammed Moshiul Hoque, Md. Azad Hossain et al.
    Journal of KSU-Computer Science and Information (Q1, IF-6.9). Elsevier, 2022
    Paper
  3. LREC
    MemoSen: A Multimodal Dataset for Sentiment Analysis of Memes
    Eftekhar Hossain , Omar Sharif, and Mohammed Moshiul Hoque
    In Proc. of LREC, 2022
    Paper Code
  4. ACL
    M-BAD: A Multilabel Dataset for Detecting Aggressive Texts and Their Targets
    Omar Sharif, Eftekhar Hossain , and Mohammed Moshiul Hoque
    CONSTRAINT Workshop. ACL, 2022
    Paper
  5. Journal
    A Deep Attentive Multimodal Learning Approach for Disaster Identification from Social Media Posts
    Eftekhar Hossain , Mohammed Moshiul Hoque, Enamul Hoque, and Md. Saiful Islam
    IEEE Access (Q1, IF-3.367), 2022
    Paper Code

2021

  1. EACL
    Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes
    Eftekhar Hossain , Omar Sharif, and Mohammed Moshiul Hoque
    DravidianLangTech Workshop (Shared Task). EACL, 2021
    Paper Code
  2. EACL
    Offensive Language Detection from Multilingual Code-Mixed Text using Transformers
    Omar Sharif, Eftekhar Hossain , and Mohammed Moshiul Hoque
    DravidianLangTech Workshop (Shared Task). EACL, 2021
    Paper Code
  3. EACL
    Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner
    Eftekhar Hossain , Omar Sharif, and Mohammed Moshiul Hoque
    LT-EDI Workshop (Shared Task). EACL, 2021
    Paper Code
  4. Springer
    Sentiment Polarity Detection on Bengali Book Reviews Using Multinomial Naive Bayes
    Eftekhar Hossain , Omar Sharif, and Mohammed Moshiul Hoque
    In Proc. of Advanced Computing and Intelligent Engineering. Springer, 2021
    Paper