mlsanityData to 7 Oct 2026

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

arXiv 2409.06107 ↗First posted 9 Sep 2024cs.CL cs.AIcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 9 Sep 2024.

Builds on

16 of 21 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2024Humans or LLMs as the Judge? A Study on Judgement Biasescited by 314
  6. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  7. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  8. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Modelscited by 171
  9. 2023MART: Improving LLM Safety with Multi-round Automatic Red-Teamingcited by 161
  10. 2023AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Modelcited by 93
  11. 2023Self-Evaluation Improves Selective Generation in Large Language Modelscited by 74
  12. 2022Black-box Prompt Learning for Pre-trained Language Modelscited by 70
4 more
  1. 2024Designing Heterogeneous LLM Agents for Financial Sentiment Analysiscited by 48
  2. 2024Molecular Facts: Desiderata for Decontextualization in LLM Fact Verificationcited by 42
  3. 2023Robust Safety Classifier for Large Language Models: Adversarial Prompt Shieldcited by 24
  4. 2024Optimization Techniques for Sentiment Analysis Based on LLM (GPT-3)cited by 7

Built on by

Not cited yet.