Search Results for author: Hamed Firooz

Found 21 papers, 9 papers with code

Modality-specific Distillation

no code implementations NAACL (maiworkshop) 2021 Woojeong Jin, Maziar Sanjabi, Shaoliang Nie, Liang Tan, Xiang Ren, Hamed Firooz

In this paper, we propose modality-specific distillation (MSD) to effectively transfer knowledge from a teacher on multimodal datasets.

Knowledge Distillation Meta-Learning

Resprompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models

no code implementations7 Oct 2023 Song Jiang, Zahra Shakeri, Aaron Chan, Maziar Sanjabi, Hamed Firooz, Yinglong Xia, Bugra Akyildiz, Yizhou Sun, Jinchao Li, Qifan Wang, Asli Celikyilmaz

Breakdown analysis further highlights RESPROMPT particularly excels in complex multi-step reasoning: for questions demanding at least five reasoning steps, RESPROMPT outperforms the best CoT based benchmarks by a remarkable average improvement of 21. 1% on LLaMA-65B and 14. 3% on LLaMA2-70B.

Math

Identifying Interpretable Subspaces in Image Representations

1 code implementation20 Jul 2023 Neha Kalibhat, Shweta Bhardwaj, Bayan Bruss, Hamed Firooz, Maziar Sanjabi, Soheil Feizi

Although many existing approaches interpret features independently, we observe in state-of-the-art self-supervised and supervised models, that less than 20% of the representation space can be explained by individual features.

counterfactual Language Modelling

Meta-training with Demonstration Retrieval for Efficient Few-shot Learning

no code implementations30 Jun 2023 Aaron Mueller, Kanika Narang, Lambert Mathias, Qifan Wang, Hamed Firooz

Meta-training allows one to leverage smaller models for few-shot generalization in a domain-general and task-agnostic manner; however, these methods alone results in models that may not have sufficient parameterization or knowledge to adapt quickly to a large variety of tasks.

Few-Shot Learning QNLI +3

Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

1 code implementation CVPR 2023 Ajinkya Tejankar, Maziar Sanjabi, Qifan Wang, Sinong Wang, Hamed Firooz, Hamed Pirsiavash, Liang Tan

It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on it, the final model will have a backdoor that the adversary can exploit.

Data Poisoning Self-Supervised Learning

COFFEE: Counterfactual Fairness for Personalized Text Generation in Explainable Recommendation

no code implementations14 Oct 2022 Nan Wang, Qifan Wang, Yi-Chia Wang, Maziar Sanjabi, Jingzhou Liu, Hamed Firooz, Hongning Wang, Shaoliang Nie

However, the bias inherent in user written text, often used for PTG model training, can inadvertently associate different levels of linguistic quality with users' protected attributes.

counterfactual Counterfactual Inference +4

FRAME: Evaluating Rationale-Label Consistency Metrics for Free-Text Rationales

no code implementations2 Jul 2022 Aaron Chan, Shaoliang Nie, Liang Tan, Xiaochang Peng, Hamed Firooz, Maziar Sanjabi, Xiang Ren

Following how humans communicate, free-text rationales aim to use natural language to explain neural language model (LM) behavior.

Hallucination Language Modelling +2

Detecting and Understanding Harmful Memes: A Survey

1 code implementation9 May 2022 Shivam Sharma, Firoj Alam, Md. Shad Akhtar, Dimitar Dimitrov, Giovanni Da San Martino, Hamed Firooz, Alon Halevy, Fabrizio Silvestri, Preslav Nakov, Tanmoy Chakraborty

One interesting finding is that many types of harmful memes are not really studied, e. g., such featuring self-harm and extremism, partly due to the lack of suitable datasets.

Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

no code implementations Findings (ACL) 2022 Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, Hamed Firooz

Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain.

Entity Linking Re-Ranking

Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features

no code implementations3 Mar 2022 Neha Kalibhat, Kanika Narang, Hamed Firooz, Maziar Sanjabi, Soheil Feizi

Fine-tuning with Q-Score regularization can boost the linear probing accuracy of SSL models by up to 5. 8% on ImageNet-100 and 3. 7% on ImageNet-1K compared to their baselines.

Self-Supervised Learning

BARACK: Partially Supervised Group Robustness With Guarantees

no code implementations31 Dec 2021 Nimit S. Sohoni, Maziar Sanjabi, Nicolas Ballas, Aditya Grover, Shaoliang Nie, Hamed Firooz, Christopher Ré

Theoretically, we provide generalization bounds for our approach in terms of the worst-group performance, which scale with respect to both the total number of training points and the number of training points with group labels.

Fairness Generalization Bounds

A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision

no code implementations27 Dec 2021 Ajinkya Tejankar, Maziar Sanjabi, Bichen Wu, Saining Xie, Madian Khabsa, Hamed Pirsiavash, Hamed Firooz

In this paper, we focus on teasing out what parts of the language supervision are essential for training zero-shot image classification models.

Classification Image Captioning +3

UNIREX: A Unified Learning Framework for Language Model Rationale Extraction

1 code implementation BigScience (ACL) 2022 Aaron Chan, Maziar Sanjabi, Lambert Mathias, Liang Tan, Shaoliang Nie, Xiaochang Peng, Xiang Ren, Hamed Firooz

An extractive rationale explains a language model's (LM's) prediction on a given task instance by highlighting the text inputs that most influenced the prediction.

Language Modelling text-classification +1

Detecting Propaganda Techniques in Memes

1 code implementation ACL 2021 Dimitar Dimitrov, Bishr Bin Ali, Shaden Shaar, Firoj Alam, Fabrizio Silvestri, Hamed Firooz, Preslav Nakov, Giovanni Da San Martino

We further create and release a new corpus of 950 memes, carefully annotated with 22 propaganda techniques, which can appear in the text, in the image, or in both.

SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images

1 code implementation SEMEVAL 2021 Dimitar Dimitrov, Bishr Bin Ali, Shaden Shaar, Firoj Alam, Fabrizio Silvestri, Hamed Firooz, Preslav Nakov, Giovanni Da San Martino

We describe SemEval-2021 task 6 on Detection of Persuasion Techniques in Texts and Images: the data, the annotation guidelines, the evaluation setup, the results, and the participating systems.

Adversarial Evaluation of Multimodal Models under Realistic Gray Box Assumption

no code implementations25 Nov 2020 Ivan Evtimov, Russel Howes, Brian Dolhansky, Hamed Firooz, Cristian Canton Ferrer

This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only) models.

General Classification Text Augmentation

Supervised Multimodal Bitransformers for Classifying Images and Text

6 code implementations6 Sep 2019 Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, Davide Testuggine

Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks.

 Ranked #1 on Natural Language Inference on V-SNLI (using extra training data)

General Classification Natural Language Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.