Papers with influence functions

5 papers
RELexED: Retrieval-Enhanced Legal Summarization with Exemplar Diversity (2025.findings-naacl)

Copied to clipboard

Challenge: Current approaches to legal summarization struggle with content theme deviation and inconsistent writing styles due to the content of the source document.
Approach: They propose a retrieval-augmented framework that utilizes exemplar summaries along with the source document to guide the model.
Outcome: The proposed model outperforms models that do not utilize exemplars and those that rely on similarity-based exemplar selection.
Interpreting Twitter User Geolocation (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for identifying user geolocation suffer from a lack of interpretability on the corresponding results.
Approach: They adopt influence functions to interpret the behavior of GNN-based models by identifying the importance of training users when predicting locations.
Outcome: The proposed method provides meaningful explanations on prediction results and also uncovers the so-called "black-box" GNN-based models by investigating the effect of individual nodes.
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have highlighted the need for effective unlearning mechanisms to comply with data regulations and ethical AI practices.
Approach: They propose a second-order optimization-based LLM unlearning framework which extends the static, one-shot model update using influence unlearning to a dynamic, iterative unlearning process.
Outcome: The proposed framework outperforms first-order methods across unlearning tasks, models, and metrics.
Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions (2020.acl-main)

Copied to clipboard

Challenge: Modern deep learning models for NLP are notoriously opaque, and this has motivated efforts to design example-specific approaches to interpret such models.
Approach: They propose to use influence functions to explain models by highlighting important words in input text to provide models with an explanation.
Outcome: The proposed approach is particularly useful for natural language inference, a task in which ‘saliency maps’ may not have clear interpretation.
Data Efficient RLVR via Off-Policy Influence Guidance (2026.acl-long)

Copied to clipboard

Challenge: Existing data selection methods for RLVR are heuristic-based, lacking theoretical guarantees and generalizability.
Approach: They propose an off-policy influence estimation method that approximates data influence using offline trajectories.
Outcome: The proposed method reduces the computational cost of policy rollouts and improves storage and computation efficiency.

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