mlsanityData to 7 Oct 2026

Inverse Language Modeling towards Robust and Grounded LLMs

arXiv 2510.01929 ↗First posted 2 Oct 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

The current landscape of defensive mechanisms for LLMs is fragmented and underdeveloped, unlike prior work on classifiers. To further promote adversarial robustness in LLMs, we propose Inverse Language Modeling (ILM), a unified framework that simultaneously 1) improves the robustness of LLMs to input perturbations, and, at the same time, 2) enables native grounding by inverting model outputs to identify potentially toxic or unsafe input triggers. ILM transforms LLMs from static generators into analyzable and robust systems, potentially helping RED teaming. ILM can lay the foundation for next-generation LLMs that are not only robust and grounded but also fundamentally more controllable and trustworthy. The code is publicly available at github.com/davegabe/pag-llm.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

19 of 26 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  6. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 738
  7. 2023Detecting Language Model Attacks with Perplexitycited by 411
  8. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 276
  9. 2016Using the Output Embedding to Improve Language Modelscited by 266
  10. 2024AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMscited by 185
  11. 2024AdvPrompter: Fast Adaptive Adversarial Prompting for LLMscited by 146
  12. 2020The Multilingual Amazon Reviews Corpuscited by 142
7 more
  1. 2024Efficient Adversarial Training in LLMs with Continuous Attackscited by 104
  2. 2016Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modelingcited by 87
  3. 2024Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Samplingcited by 33
  4. 2022Do Perceptually Aligned Gradients Imply Adversarial Robustness?cited by 15
  5. 2024Shedding More Light on Robust Classifiers under the lens of Energy-based Modelscited by 9
  6. 2023Prompts have evil twinscited by 7
  7. 2024Evil twins are not that evil: Qualitative insights into machine-generated promptscited by 5

Built on by

Not cited yet.