Editing Common Sense in Transformers (2023.emnlp-main)

Copied to clipboard

Challenge: Currently, the performance of transformer-based model editing methods is limited to statements about encyclopedic knowledge with a single correct answer.
Approach: They propose to improve MEMIT's model editing algorithm by varying edit tokens and improving the layer selection strategy to improve commonsense knowledge.
Outcome: The MEMIT editing algorithm outperforms baseline models on PEP3k and 20Q datasets while fine-tuning baselines shows significant trade-offs.

Similar Papers

Interpretability-based Tailored Knowledge Editing in Transformers (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for modifying in-context learning fail to analyze the instability of in-constitu learning outcomes.
Approach: They propose a model-based knowledge editing method that considers the unique information flow of each sample and aims to correct errors without costly retraining.
Outcome: The proposed method exploits the critical role of feed-forward MLPs in decoder-only models and reveals diverse attribute recall across transformer layers, guiding edits to specific features at different depths and mitigating over-editing issues.
One Mask to Rule Them All: On Hidden Facts after Editing and How to Find Them (2026.findings-acl)

Copied to clipboard

Challenge: Knowledge editing methods such as ROME and MEMIT update factual associations by modifying MLP weights.
Approach: They propose to use a mask to reverse edits by eliminating overattention in later layers . they also show that injecting the mask during editing drops editing success from 98% to 38% .
Outcome: The proposed method reverses edits by eliminating overattention in later layers and drops editing success from 98% to 38%.
Mass-Editing Memory with Attention in Transformers: A cross-lingual exploration of knowledge (2024.findings-acl)

Copied to clipboard

Challenge: Recent studies have explored methods for updating and modifying factual knowledge in large language models, often focusing on specific multi-layer perceptron blocks.
Approach: They propose a method that allows users to edit factual associations without catastrophic forgetting.
Outcome: The proposed method achieves 10% increase in magnitude metrics while requiring minimal parameter modifications.
Do Transformer Modifications Transfer Across Implementations and Applications? (2021.emnlp-main)

Copied to clipboard

Challenge: Currently, the Transformer is the de facto architecture of choice for processing sequential data.
Approach: They evaluate the Transformer architecture and its modifications in a shared experimental setting . they conjecture that performance improvements may strongly depend on implementation details .
Outcome: The proposed improvements do not significantly improve performance, the authors find . the proposed improvements are either developed in the same codebase or are minor changes .
CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension (2023.findings-eacl)

Copied to clipboard

Challenge: Existing frameworks for referring expression comprehension with commonsense knowledge are lacking in the field of multimodal referring .
Approach: They propose a framework for commonsense knowledge Enhanced Transformers which integrates commonsensible knowledge into representations of objects in an image.
Outcome: The proposed framework improves on the existing state of the art in referring expression comprehension with commonsense knowledge (CK-Transformer) it achieves 3.14% accuracy over the existing framework.
TARE: Lightweight Token-Aware Representation Editing for Fine-tuning Transformer-like Models (2026.acl-long)

Copied to clipboard

Challenge: Existing PEFT methods can be costly and underfit token-level contexts.
Approach: They propose a PEFT method that performs fine-grained, token-specific edits with a small additional inference overhead and minimal tuning.
Outcome: The proposed method outperforms state-of-the-art methods in 8 tasks and GLUE with a minimal tuning overhead and inference overhead.
Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability Problems (2025.acl-long)

Copied to clipboard

Challenge: Transformer models exhibit minimal scale and noise invariance, along with limited vocabulary and number invariancy.
Approach: They probe the generalisation prowess of Transformer models with respect to the hitherto unexplored domain of numerical satisfiability problems.
Outcome: The proposed models exhibit minimal scale and noise invariance, along with limited vocabulary and number invariancy.
Transformer-specific Interpretability (2024.eacl-tutorials)

Copied to clipboard

Challenge: Transformers are dominant play-ers in various scientific fields, but their inner workings remain opaque.
Approach: This tutorial presents a trending approach to interpreting Transformers . it uses specific features of the Transformer architecture to quantify context- mixing interactions .
Outcome: This tutorial aims to show how a new trending approach can be applied to Transformer-based models.
Identifying the limits of transformers when performing model-checking with natural language (2023.eacl-main)

Copied to clipboard

Challenge: Recent studies have focused on transformer models’ ability to perform reasoning on text, but the above question has not been adequately answered.
Approach: They investigated the problem of model-checking with natural language to determine whether transformers can comprehend logical semantics in natural language.
Outcome: The proposed model-checking problem is suited to address this issue but is untouched in natural language inference research.
What Context Features Can Transformer Language Models Use? (2021.acl-long)

Copied to clipboard

Challenge: Recent studies show that transformer-based language models benefit from conditioning on contexts of hundreds to thousands of previous tokens.
Approach: They propose to use lexical and structural information to ablate usable information in transformer language models.
Outcome: The proposed model improves when conditioning on contexts of thousands of previous tokens.

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