# Doppelg"anger's Watch: A Split Objective Approach to Large Language Models

arXiv: https://arxiv.org/abs/2409.06107 · HTML: https://mlsanity.com/paper/2409.06107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 9 Sep 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Humans or LLMs as the Judge? A Study on Judgement Biases](https://mlsanity.com/paper/2402.10669/) (2024)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models](https://mlsanity.com/paper/2305.13873/) (2023)
- [MART: Improving LLM Safety with Multi-round Automatic Red-Teaming](https://mlsanity.com/paper/2311.07689/) (2023)
- [AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model](https://mlsanity.com/paper/2309.16058/) (2023)
- [Self-Evaluation Improves Selective Generation in Large Language Models](https://mlsanity.com/paper/2312.09300/) (2023)
- [Black-box Prompt Learning for Pre-trained Language Models](https://mlsanity.com/paper/2201.08531/) (2022)
- [Designing Heterogeneous LLM Agents for Financial Sentiment Analysis](https://mlsanity.com/paper/2401.05799/) (2024)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield](https://mlsanity.com/paper/2311.00172/) (2023)
- [Optimization Techniques for Sentiment Analysis Based on LLM (GPT-3)](https://mlsanity.com/paper/2405.09770/) (2024)

## Abstract (arXiv)

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.