paper-with-me

홈 › Papers

TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs

2024-07-06 · Cheng Wang, Xinyang Lu, See-Kiong Ng, Bryan Kian Hsiang Low

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.

📄 PDF Abstract BibTeX arXiv:2407.04981

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeContrastive LearningNatural Language Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

BMRL: Bi-Modal Guided Multi-Perspective Representation Learning for Zero-Shot Deepfake Attribution

2025-04-19 · Yaning Zhang, Jiahe Zhang, Chunjie Ma, Weili Guan 외

The challenge of tracing the source attribution of forged faces has gained significant attention due to the rapid advancement of generative models. However, existing deepfake attribution (DFA) works primarily focus on th…

AttributeFace ParsingFace SwappingRepresentation Learning

Dual Path Attribution: Efficient Attribution for SwiGLU-Transformers through Layer-Wise Target Propagation

2026-03-20 · Lasse Marten Jantsch, Dong-Jae Koh, Seonghyeon Lee, Young-Kyoon Suh arxiv

Understanding the internal mechanisms of transformer-based large language models (LLMs) is crucial for their reliable deployment and effective operation. While recent efforts have yielded a plethora of attribution method…

Computational Efficiency

REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces

2026-06-08 · Xiaofeng Lin, Yingxu Wang, Tung Sum Thomas Kwok, Daniel Guo 외 arxiv

Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind, especially in the \emph{silent failure} regi…

Contrastive Pseudo Learning for Open-World DeepFake Attribution

2023-09-20 · ICCV 2023 1 · Zhimin Sun, Shen Chen, Taiping Yao, Bangjie Yin 외

The challenge in sourcing attribution for forgery faces has gained widespread attention due to the rapid development of generative techniques. While many recent works have taken essential steps on GAN-generated faces, mo…

DeepFake DetectionFace SwappingPseudo Label

Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs

2026-02-02 · Wenbo Pan, Zhichao Liu, Xianlong Wang, Haining Yu 외 arxiv

Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as modern LLMs increasingly rely on extended reasoning chains, existing schemes…