paper-with-me

홈 › Papers

Doppelgänger's Watch: A Split Objective Approach to Large Language Models

2024-09-09 · Shervin Ghasemlou, Ashish Katiyar, Aparajita Saraf, Seungwhan Moon, Mangesh Pujari, Pinar Donmez, Babak Damavandi, Anuj Kumar

In this paper, we investigate the problem of "generation supervision" in large language models, and present a novel bicameral architecture to separate supervision signals from their core capability, helpfulness. Doppelg\"anger, a new module parallel to the underlying language model, supervises the generation of each token, and learns to concurrently predict the supervision score(s) of the sequences up to and including each token. In this work, we present the theoretical findings, and leave the report on experimental results to a forthcoming publication.

📄 PDF Abstract BibTeX arXiv:2409.06107

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

Reliable Detection of Doppelgängers based on Deep Face Representations

2022-01-21 · Christian Rathgeb, Daniel Fischer, Pawel Drozdowski, Christoph Busch

Doppelg\"angers (or lookalikes) usually yield an increased probability of false matches in a facial recognition system, as opposed to random face image pairs selected for non-mated comparison trials. In this work, we ass…

Face Recognition

Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack

2025-06-17 · Daewon Kang, YeongHwan Shin, Doyeon Kim, Kyu-Hwan Jung 외

Since the advent of large language models, prompt engineering now enables the rapid, low-effort creation of diverse autonomous agents that are already in widespread use. Yet this convenience raises urgent concerns about …

Adversarial AttackPrompt Engineering

Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features

2024-12-08 · CVPR 2025 1 · Yuanbo Xiangli, Ruojin Cai, HanYu Chen, Jeffrey Byrne 외

Accurate 3D reconstruction is frequently hindered by visual aliasing, where visually similar but distinct surfaces (aka, doppelgangers), are incorrectly matched. These spurious matches distort the structure-from-motion (…

3D Reconstruction

Doppelgangers: Learning to Disambiguate Images of Similar Structures

2023-09-05 · ICCV 2023 1 · Ruojin Cai, Joseph Tung, Qianqian Wang, Hadar Averbuch-Elor 외

We consider the visual disambiguation task of determining whether a pair of visually similar images depict the same or distinct 3D surfaces (e.g., the same or opposite sides of a symmetric building). Illusory image match…

3D ReconstructionBinary Classification

Doppelgangers and Adversarial Vulnerability

2025-01-01 · CVPR 2025 1 · George Kamberov

Many machine learning (ML) classifiers are claimed to outperform humans, but they still make mistakes that humans do not. The most notorious examples of such mistakes are adversarial visual metamers. This paper aims …