paper-with-me

Papers

ADAG: Automatically Describing Attribution Graphs

2026-04-08 · Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt, Sarah Schwettmann arxiv

In language model interpretability research, \textbf{circuit tracing} aims to identify which internal features causally contributed to a particular output and how they affected each other, with the goal of explaining the computations underlying some behaviour. However, all prior circuit tracing work has relied on ad-hoc human interpretation of the role that each feature in the circuit plays, via manual inspection of data artifacts such as the dataset examples the component activates on. We introduce \textbf{ADAG}, an end-to-end pipeline for describing these attribution graphs which is fully automated. To achieve this, we introduce \textit{attribution profiles} which quantify the functional role of a feature via its input and output gradient effects. We then introduce a novel clustering algorithm for grouping features, and an LLM explainer--simulator setup which generates and scores natural-language explanations of the functional role of these feature groups. We run our system on known human-analysed circuit-tracing tasks and recover interpretable circuits, and further show ADAG can find steerable clusters which are responsible for a harmful advice jailbreak in Llama 3.1 8B Instruct.

📄 PDF Abstract BibTeX arXiv:2604.07615

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Benchmarking Large Language Models in Complex Question Answering Attribution using Knowledge Graphs

2024-01-26 · Nan Hu, Jiaoyan Chen, Yike Wu, Guilin Qi 외

The attribution of question answering is to provide citations for supporting generated statements, and has attracted wide research attention. The current methods for automatically evaluating the attribution, which are of…

BenchmarkingKnowledge GraphsQuestion Answering

AdaGCL: Adaptive Subgraph Contrastive Learning to Generalize Large-scale Graph Training

2022-10-17 · ACM International Conference on Information & Knowledge Management (CIKM) 2022 10 · Yili Wang, Kaixiong Zhou, Rui Miao, Ninghao Liu 외

Training graph neural networks (GNNs) with good generalizability on large-scale graphs is a challenging problem. Existing methods mainly divide the input graph into multiple subgraphs and train them in different batches …

Contrastive LearningData AugmentationNode Classification

AdaGNN: A multi-modal latent representation meta-learner for GNNs based on AdaBoosting

2021-08-14 · Qinyi Zhu, Yiou Xiao

As a special field in deep learning, Graph Neural Networks (GNNs) focus on extracting intrinsic network features and have drawn unprecedented popularity in both academia and industry. Most of the state-of-the-art GNN mod…

DecoderRecommendation Systems

AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models

2019-08-14 · ICLR 2021 1 · Ke Sun, Zhanxing Zhu, Zhouchen Lin

The design of deep graph models still remains to be investigated and the crucial part is how to explore and exploit the knowledge from different hops of neighbors in an efficient way. In this paper, we propose a novel RN…

Graph Neural NetworkNode Classification

AdaGC: Improving Training Stability for Large Language Model Pretraining

2025-02-16 · Guoxia Wang, Shuai Li, Congliang Chen, Jinle Zeng 외

Large Language Models (LLMs) face increasing loss spikes during scaling, undermining training stability and final performance. While gradient clipping mitigates this issue, traditional global approaches poorly handle par…

LAMBADALanguage ModelingLanguage ModellingLarge Language Model