Papers with sub-models

9 papers
Recycling a Pre-trained BERT Encoder for Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: In monolingual tasks, the number of unlearned model parameters is as huge as the number learned parameters in the BERT model.
Approach: They propose to apply a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model to Transformer-based neural machine translation (NMT) based on the Transformer.
Outcome: The proposed model is stable and efficient in low-resource settings.
Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models (2021.naacl-main)

Copied to clipboard

Challenge: Existing approaches to decompose complex tasks into simpler ones do not require annotated decompositions.
Approach: They propose a framework for building interpretable systems that learn to solve complex tasks by decomposing existing models into simpler ones solvable by existing models.
Outcome: The proposed framework is more versatile than existing explainable systems for DROP and HotpotQA datasets, is more robust than state-of-the-art blackbox (uninterpretable) systems, and generates more understandable and trustworthy explanations compared to prior work.
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference (2024.findings-eacl)

Copied to clipboard

Challenge: Large language models excel at understanding and generating human-like text, but their widespread deployment can be prohibitively expensive.
Approach: They propose a method that makes large language models dynamic without Pre-Training . they use modularity in networks and sort sub-models based on computation/accuracy in a nested manner.
Outcome: The proposed method can make large language models dynamic without pre-training and replace standard fine-tuning with sorted fine- tuning.
Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction (2024.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models may not follow human instructions and produce toxic, hallucinated, or biased content.
Approach: They propose a disperse-then-merge framework that dispersers instruction-following data into portions and trains multiple sub-models using different data portions.
Outcome: The proposed framework outperforms data curation and training regularization on standard knowledge and reasoning benchmarks.
ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty.
Approach: They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline.
Outcome: The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets.
R-AT: Regularized Adversarial Training for Natural Language Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Currently, adversarial training is a popular and powerful regularization method in the natural language domain.
Approach: They propose to regularize adversarial training via dropout by perturbing word embeddings . they find that R-AT can improve many models by reducing adversariality .
Outcome: The proposed method can reduce the inconsistency between training and testing of models with dropout.
Scaling Vision-Language Models with Sparse Mixture of Experts (2023.findings-emnlp)

Copied to clipboard

Challenge: a study explores the effectiveness of mixture-of-experts (MoE) techniques in scaling vision-language models . alayrac and colleagues demonstrate the effectiveness and performance of MoE in scaling VLMs .
Approach: They propose to use sparsely-gated mixture-of-experts techniques to scale vision-language models . they show that MoE can achieve state-of the-art performance over dense models a range of benchmarks .
Outcome: The proposed approach achieves state-of-the-art performance over dense models of equivalent computational cost.
Towards Robustifying NLI Models Against Lexical Dataset Biases (2020.acl-main)

Copied to clipboard

Challenge: Recent studies show that deep learning models exploit dataset biases without deep understanding of the language semantics.
Approach: They propose two methods to debiase models against lexical dataset biases . they use contradiction-word bias and word-overlapping bias as examples .
Outcome: The proposed method removes label bias at embedding level, while the other uses a bag-of-words sub-model to capture features likely to exploit the bias.
Collaboration of Fusion and Independence: Hypercomplex-driven Robust Multi-Modal Knowledge Graph Completion (2026.acl-long)

Copied to clipboard

Challenge: Existing multi-modal knowledge graphs lack modality-specific information and are limited in their ability to capture nuanced semantic interplay between modalities.
Approach: They propose a multi-modal knowledge graph completion method which integrates both paradigms . they use a fine-grained Entity Representation Factorization module and a Robust Relation-aware Modality Fusion module to obtain robust representations for three independent modalities and one fused modality.
Outcome: The proposed method achieves coexistence and collaboration of fused and independent modality representations while maintaining modality-specific information.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations