mlsanityData to 14 Oct 2026

Limitation Learning: Catching Adverse Dialog with GAIL

arXiv 2508.11767 ↗First posted 15 Aug 2025cs.CL cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Language-conditioned policies and VLAs

Abstract (arXiv)

Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a user given a prompt (input state), and a discriminator capable of classifying between expert and synthetic conversation. While our policy is effective, we recover results from our discriminator that indicate the limitations of dialog models. We argue that this technique can be used to identify adverse behavior of arbitrary data models common for dialog oriented tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Language-conditioned policies and VLAs, one of 13 directions in Offline RL and imitation learning from data. Builds on 8 of its 9 references that are in the map. First posted on arXiv 15 Aug 2025.

Builds on

8 of 9 references.

Closest ancestors · 1

Same direction, newest first

  1. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning9 Dec

Other references · 7

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  5. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 406
  6. 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
  7. 2017Adversarial Learning for Neural Dialogue Generationcited by 103

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2019Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts
  2. 2020Show Us the Way: Learning to Manage Dialog from Demonstrations
  3. 2020Human-centric Dialog Training via Offline Reinforcement Learning
  4. 2020Learning Dialog Policies from Weak Demonstrations
  5. 2021Integrating Pretrained Language Model for Dialogue Policy Learning
  6. 2023Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization
  7. 2026Robust Critics: Defending LLMs Against Multi-Turn Attacks
  8. 2019Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog