Search Results for author: Hamid Palangi

Found 38 papers, 17 papers with code

Improving Black-box Robustness with In-Context Rewriting

1 code implementation13 Feb 2024 Kyle O'Brien, Nathan Ng, Isha Puri, Jorge Mendez, Hamid Palangi, Yoon Kim, Marzyeh Ghassemi, Thomas Hartvigsen

Most techniques for improving OOD robustness are not applicable to settings where the model is effectively a black box, such as when the weights are frozen, retraining is costly, or the model is leveraged via an API.

News Classification

Exploring Group and Symmetry Principles in Large Language Models

no code implementations9 Feb 2024 Shima Imani, Hamid Palangi

Large Language Models (LLMs) have demonstrated impressive performance across a wide range of applications; however, assessing their reasoning capabilities remains a significant challenge.

Arithmetic Reasoning Negation

A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia

1 code implementation4 Dec 2023 Giovanni Monea, Maxime Peyrard, Martin Josifoski, Vishrav Chaudhary, Jason Eisner, Emre Kiciman, Hamid Palangi, Barun Patra, Robert West

Yet the mechanisms underlying this contextual grounding remain unknown, especially in situations where contextual information contradicts factual knowledge stored in the parameters, which LLMs also excel at recalling.

counterfactual Language Modelling +1

Diversity of Thought Improves Reasoning Abilities of LLMs

no code implementations11 Oct 2023 Ranjita Naik, Varun Chandrasekaran, Mert Yuksekgonul, Hamid Palangi, Besmira Nushi

Large language models (LLMs) are documented to struggle in settings that require complex reasoning.

Teaching Language Models to Hallucinate Less with Synthetic Tasks

no code implementations10 Oct 2023 Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Awadallah, Ece Kamar

We also find that optimizing the system message rather than the model weights can be critical; fine-tuning the entire model on the synthetic task can counterintuitively increase hallucination.

Abstractive Text Summarization Hallucination +3

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models

no code implementations26 Sep 2023 Mert Yuksekgonul, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi

We investigate the internal behavior of Transformer-based Large Language Models (LLMs) when they generate factually incorrect text.

Gender-tuning: Empowering Fine-tuning for Debiasing Pre-trained Language Models

no code implementations20 Jul 2023 Somayeh Ghanbarzadeh, Yan Huang, Hamid Palangi, Radames Cruz Moreno, Hamed Khanpour

Recent studies have revealed that the widely-used Pre-trained Language Models (PLMs) propagate societal biases from the large unmoderated pre-training corpora.

Language Modelling Masked Language Modeling

Improving the Reusability of Pre-trained Language Models in Real-world Applications

no code implementations19 Jul 2023 Somayeh Ghanbarzadeh, Hamid Palangi, Yan Huang, Radames Cruz Moreno, Hamed Khanpour

The reusability of state-of-the-art Pre-trained Language Models (PLMs) is often limited by their generalization problem, where their performance drastically decreases when evaluated on examples that differ from the training dataset, known as Out-of-Distribution (OOD)/unseen examples.

Language Modelling Masked Language Modeling

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

3 code implementations5 Jun 2023 Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, Ahmed Awadallah

To address these challenges, we develop Orca (We are working with our legal team to publicly release a diff of the model weights in accordance with LLaMA's release policy to be published at https://aka. ms/orca-lm), a 13-billion parameter model that learns to imitate the reasoning process of LFMs.

Imitation Learning Knowledge Distillation

Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning

no code implementations8 Apr 2023 Yu Yang, Besmira Nushi, Hamid Palangi, Baharan Mirzasoleiman

Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments.

Attribute

Sparks of Artificial General Intelligence: Early experiments with GPT-4

2 code implementations22 Mar 2023 Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, Yi Zhang

We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models.

Arithmetic Reasoning Math Word Problem Solving

An Empirical Study of Metrics to Measure Representational Harms in Pre-Trained Language Models

1 code implementation22 Jan 2023 Saghar Hosseini, Hamid Palangi, Ahmed Hassan Awadallah

Large-scale Pre-Trained Language Models (PTLMs) capture knowledge from massive human-written data which contains latent societal biases and toxic contents.

Language Modelling

Benchmarking Spatial Relationships in Text-to-Image Generation

1 code implementation20 Dec 2022 Tejas Gokhale, Hamid Palangi, Besmira Nushi, Vibhav Vineet, Eric Horvitz, Ece Kamar, Chitta Baral, Yezhou Yang

We investigate the ability of T2I models to generate correct spatial relationships among objects and present VISOR, an evaluation metric that captures how accurately the spatial relationship described in text is generated in the image.

Benchmarking Text-to-Image Generation

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

1 code implementation NeurIPS 2023 Thomas Hartvigsen, Swami Sankaranarayanan, Hamid Palangi, Yoon Kim, Marzyeh Ghassemi

We propose GRACE, a lifelong model editing method, which implements spot-fixes on streaming errors of a deployed model, ensuring minimal impact on unrelated inputs.

Model Editing World Knowledge

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

1 code implementation20 Nov 2022 Abdelrahman Zayed, Prasanna Parthasarathi, Goncalo Mordido, Hamid Palangi, Samira Shabanian, Sarath Chandar

The fairness achieved by our method surpasses that of data augmentation on three text classification datasets, using no more than half of the examples in the augmented dataset.

counterfactual Data Augmentation +3

NaturalAdversaries: Can Naturalistic Adversaries Be as Effective as Artificial Adversaries?

no code implementations8 Nov 2022 Saadia Gabriel, Hamid Palangi, Yejin Choi

While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data distributions.

Natural Language Understanding text-classification +1

Robustness Analysis of Video-Language Models Against Visual and Language Perturbations

1 code implementation5 Jul 2022 Madeline C. Schiappa, Shruti Vyas, Hamid Palangi, Yogesh S. Rawat, Vibhav Vineet

Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning.

Language Modelling Retrieval +2

ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

1 code implementation ACL 2022 Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, Ece Kamar

To help mitigate these issues, we create ToxiGen, a new large-scale and machine-generated dataset of 274k toxic and benign statements about 13 minority groups.

Hate Speech Detection Language Modelling

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization

1 code implementation NAACL 2021 Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao

On several syntactic and semantic probing tasks, we demonstrate the emergent structural information in the role vectors and improved syntactic interpretability in the TPR layer outputs.

Abstractive Text Summarization

Compositional Processing Emerges in Neural Networks Solving Math Problems

1 code implementation19 May 2021 Jacob Russin, Roland Fernandez, Hamid Palangi, Eric Rosen, Nebojsa Jojic, Paul Smolensky, Jianfeng Gao

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition.

Math Mathematical Reasoning

Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"

no code implementations ICML 2020 Saeed Amizadeh, Hamid Palangi, Oleksandr Polozov, Yichen Huang, Kazuhito Koishida

To address this, we propose (1) a framework to isolate and evaluate the reasoning aspect of VQA separately from its perception, and (2) a novel top-down calibration technique that allows the model to answer reasoning questions even with imperfect perception.

Graph Generation Question Answering +4

Novel Human-Object Interaction Detection via Adversarial Domain Generalization

no code implementations22 May 2020 Yuhang Song, Wenbo Li, Lei Zhang, Jianwei Yang, Emre Kiciman, Hamid Palangi, Jianfeng Gao, C. -C. Jay Kuo, Pengchuan Zhang

We study in this paper the problem of novel human-object interaction (HOI) detection, aiming at improving the generalization ability of the model to unseen scenarios.

Domain Generalization Human-Object Interaction Detection +1

HUBERT Untangles BERT to Improve Transfer across NLP Tasks

1 code implementation25 Oct 2019 Mehrad Moradshahi, Hamid Palangi, Monica S. Lam, Paul Smolensky, Jianfeng Gao

We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model.

Language Modelling

Mapping Natural-language Problems to Formal-language Solutions Using Structured Neural Representations

2 code implementations ICML 2020 Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao

The encoder of TP-N2F employs TPR `binding' to encode natural-language symbolic structure in vector space and the decoder uses TPR `unbinding' to generate, in symbolic space, a sequential program represented by relational tuples, each consisting of a relation (or operation) and a number of arguments.

Program Synthesis Text Generation

Natural- to formal-language generation using Tensor Product Representations

no code implementations25 Sep 2019 Kezhen Chen, Qiuyuan Huang, Hamid Palangi, Paul Smolensky, Kenneth D. Forbus, Jianfeng Gao

Generating formal-language represented by relational tuples, such as Lisp programs or mathematical expressions, from a natural-language input is an extremely challenging task because it requires to explicitly capture discrete symbolic structural information from the input to generate the output.

Math Program Synthesis +1

Unified Vision-Language Pre-Training for Image Captioning and VQA

3 code implementations24 Sep 2019 Luowei Zhou, Hamid Palangi, Lei Zhang, Houdong Hu, Jason J. Corso, Jianfeng Gao

The model is unified in that (1) it can be fine-tuned for either vision-language generation (e. g., image captioning) or understanding (e. g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models.

Image Captioning Question Answering +2

Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators

no code implementations22 Sep 2019 Kuang-Huei Lee, Hamid Palangi, Xi Chen, Houdong Hu, Jianfeng Gao

In this work, we tackle two fundamental language-and-vision tasks: image-text matching and image captioning, and demonstrate that neural scene graph generators can learn effective visual relation features to facilitate grounding language to visual relations and subsequently improve the two end applications.

Image Captioning Image-text matching +2

Question-Answering with Grammatically-Interpretable Representations

no code implementations23 May 2017 Hamid Palangi, Paul Smolensky, Xiaodong He, Li Deng

In our application of TPRN, internal representations learned by end-to-end optimization in a deep neural network performing a textual question-answering (QA) task can be interpreted using basic concepts from linguistic theory.

Inductive Bias Question Answering

Distributed Compressive Sensing: A Deep Learning Approach

no code implementations20 Aug 2015 Hamid Palangi, Rabab Ward, Li Deng

As the proposed method is a data driven method, it is only applicable when training data is available.

Compressive Sensing

Learning Input and Recurrent Weight Matrices in Echo State Networks

no code implementations13 Nov 2013 Hamid Palangi, Li Deng, Rabab K. Ward

In this paper, we devise a special technique that take advantage of this linearity in the output units of an ESN, to learn the input and recurrent matrices.

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