mlsanityData to 7 Oct 2026

Language Model Inversion through End-to-End Differentiation

arXiv 2602.11044 ↗First posted 11 Feb 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains an open problem. We formulate this problem as a classical gradient-based optimisation. First, we propose a simple algorithm to achieve end-to-end differentiability of a given (frozen) LM and then find optimised prompts via gradient descent. Our central insight is to view LMs as functions operating on sequences of distributions over tokens (rather than the traditional view as functions on sequences of tokens). Our experiments and ablations demonstrate that our DLM-powered inversion can reliably and efficiently optimise prompts of lengths 10 and 80 for targets of length 20, for several white-box LMs (out-of-the-box).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

27 of 33 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  6. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  8. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  9. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  10. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  11. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  12. 2023Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discoverycited by 329
15 more
  1. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  2. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  3. 2020Information Leakage in Embedding Modelscited by 199
  4. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  5. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 187
  6. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 168
  7. 2017Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbolscited by 123
  8. 2017Backpropagation through the Void: Optimizing control variates for black-box gradient estimationcited by 104
  9. 2017REBAR: Low-variance, unbiased gradient estimates for discrete latent variable modelscited by 78
  10. 2023Language Model Inversioncited by 66
  11. 2024Efficient Prompting Methods for Large Language Models: A Surveycited by 46
  12. 2024Extracting Prompts by Inverting LLM Outputscited by 40
  13. 2020On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimatorcited by 11
  14. 2025Better Language Model Inversion by Compactly Representing Next-Token Distributionscited by 9
  15. 2025GPT, But Backwards: Exactly Inverting Language Model Outputscited by 2

Built on by

Not cited yet.