What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing paradigms for multi-task training involve a shared pre-trained language model and a small, thin network (head) given an input, a target head is the head that is selected for outputting the final prediction. |
| Approach: | They examine the behaviour of non-target heads when given input that belongs to a different task than the one they were trained for. |
| Outcome: | The non-target heads exhibit emergent behaviour, which may explain the target task, or generalize beyond their original task. |
Similar Papers
Roles and Utilization of Attention Heads in Transformer-based Neural Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Sentence encoders based on transformer architectures have shown promising results on various natural language understanding tasks. |
| Approach: | They propose a sentence representation method that takes advantage of most influential attention heads. |
| Outcome: | The proposed method improves performance on the downstream tasks. |
Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks (2021.acl-long)
Copied to clipboard
| Challenge: | Prior research has found that only a few attention heads are important in each mono-lingual NLP task and pruning the remaining heads leads to comparable or improved performance of the model. |
| Approach: | They examine the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. |
| Outcome: | The proposed model performs better with the remaining heads pruned than with the other models, the authors show . |
Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports (2022.naacl-industry)
Copied to clipboard
Arijit Sehanobish, McCullen Sandora, Nabila Abraham, Jayashri Pawar, Danielle Torres, Anasuya Das, Murray Becker, Richard Herzog, Benjamin Odry, Ron Vianu
| Challenge: | Pretrained Transformer based models finetuned on domain specific corpora have changed the landscape of NLP but training or fine-tuning these models for individual tasks can be time consuming and resource intensive. |
| Approach: | They propose to use pretrained Transformer based models finetuned on domain specific corpora to train models for individual tasks. |
| Outcome: | The proposed model can match the performance of a task specific model when the task specific models show similar representations across all of their hidden layers and their gradients are aligned, i.e. their gradient follows the same direction. |
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that multi-head attention module evolves functional specialization after multi-task training. |
| Approach: | They propose a method to quantify the degree of functional specialization in multi-head attention . they propose 'multi-task training' method to increase functional specialisation and mitigate negative information transfer . |
| Outcome: | The proposed method increases functional specialization and mitigates negative information transfer in multi-task learning without adding any parameters. |
Identifying Semantic Induction Heads to Understand In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable performance, but lack of transparency in their inference logic raises concerns about their trustworthiness. |
| Approach: | They conduct a detailed analysis of the operations of attention heads to understand their in-context learning of LLMs. |
| Outcome: | The proposed analysis of attention heads reveals that they increase the output logits of object tokens and recall objects . the proposed model is a novel approach to understand the in-context learning of large language models. |
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions (2024.emnlp-main)
Copied to clipboard
| Challenge: | Using a method to identify next-token neurons, we find that some attention heads recognize contexts relevant to predicting a token and activate a downstream token-predicting neuron accordingly. |
| Approach: | They propose a method to identify next-token neurons and determine the upstream attention heads responsible for their activity in LLMs. |
| Outcome: | The proposed method identifies next-token neurons, finds prompts that highly activate them, and determines the upstream attention heads responsible. |
Human Guided Exploitation of Interpretable Attention Patterns in Summarization and Topic Segmentation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have investigated the multi-head self-attention mechanism of transformers. |
| Approach: | They propose to use a human-in-the-loop pipeline to discover task-specific attention patterns and inject them into transformer models to improve their accuracy. |
| Outcome: | The proposed methods improve the performance of transformer models by incorporating predefined patterns into their attention matrices. |
How does Multi-Task Training Affect Transformer In-Context Capabilities? Investigations with Function Classes (2024.naacl-short)
Copied to clipboard
| Challenge: | Multi-task learning (MTL) for generalist models is a promising direction that offers transfer learning potential. |
| Approach: | They propose to combine multi-task learning (MTL) with in-context learning (ICL) to build models that can generalize to multiple tasks while being robust to out-of-distribution examples. |
| Outcome: | The proposed training strategies enable models to learn difficult tasks while mixing in prior tasks, denoted as mixed curriculum. |
Analyzing the Inner Workings of Transformers in Compositional Generalization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on compositional generalization abilities of neural models have focused on benchmarks, but the results do not reflect the underlying competence of the model. |
| Approach: | They propose to find an existing subnetwork that contributes to the generalization performance and perform causal analyses on how the model utilizes syntactic features. |
| Outcome: | The proposed model relies on syntactic features but the subnetwork with better generalization performance relies mainly on a non-compositional algorithm . |
Mixed Multi-Head Self-Attention for Neural Machine Translation (D19-56)
Copied to clipboard
| Challenge: | Recent advances in neural machine translation have been made in the field of multi-head self-attention and there is no explicit mechanism to ensure that different attention heads capture different features. |
| Approach: | They propose a novel multi-head self-attention model which models not only global and local attention but also forward and backward attention in different attention heads. |
| Outcome: | The proposed model improves on WAT17 English-Japanese and IWSLT14 German-English translation tasks without increasing the number of parameters. |