# An Adversarial Imitation Click Model for Information Retrieval

arXiv: https://arxiv.org/abs/2104.06077 · HTML: https://mlsanity.com/paper/2104.06077/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2021.

## Built on by (most cited first, 18 of 18)

- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2308.11131/) (2023)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction](https://mlsanity.com/paper/2310.09234/) (2023)
- [A Survey on Diffusion Models for Recommender Systems](https://mlsanity.com/paper/2409.05033/) (2024)
- [A Graph-Enhanced Click Model for Web Search](https://mlsanity.com/paper/2206.08621/) (2022)
- [FLIP: Fine-grained Alignment between ID-based Models and Pretrained Language Models for CTR Prediction](https://mlsanity.com/paper/2310.19453/) (2023)
- [An F-shape Click Model for Information Retrieval on Multi-block Mobile Pages](https://mlsanity.com/paper/2206.08604/) (2022)
- [MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction](https://mlsanity.com/paper/2308.01737/) (2023)
- [An Automatic Graph Construction Framework based on Large Language Models for Recommendation](https://mlsanity.com/paper/2412.18241/) (2024)
- [Enhancing ID-based Recommendation with Large Language Models](https://mlsanity.com/paper/2411.02041/) (2024)
- [Retrieval-Oriented Knowledge for Click-Through Rate Prediction](https://mlsanity.com/paper/2404.18304/) (2024)
- [Neural Click Models for Recommender Systems](https://mlsanity.com/paper/2409.20055/) (2024)
- [MTRec: Learning to Align with User Preferences via Mental Reward Models](https://mlsanity.com/paper/2509.22807/) (2025)
- [Eval4DiRec: A Unified and Systematic Evaluation Framework for Diffusion-based Recommender Systems](https://mlsanity.com/paper/2609.34404/) (2026)
- [Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems](https://mlsanity.com/paper/2210.05662/) (2022)
- [Full-Stack Optimized Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2501.13344/) (2025)
- [AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing](https://mlsanity.com/paper/2504.04706/) (2025)

## Abstract (arXiv)

Modern information retrieval systems, including web search, ads placement, and recommender systems, typically rely on learning from user feedback. Click models, which study how users interact with a ranked list of items, provide a useful understanding of user feedback for learning ranking models. Constructing "right" dependencies is the key of any successful click model. However, probabilistic graphical models (PGMs) have to rely on manually assigned dependencies, and oversimplify user behaviors. Existing neural network based methods promote PGMs by enhancing the expressive ability and allowing flexible dependencies, but still suffer from exposure bias and inferior estimation. In this paper, we propose a novel framework, Adversarial Imitation Click Model (AICM), based on imitation learning. Firstly, we explicitly learn the reward function that recovers users' intrinsic utility and underlying intentions. Secondly, we model user interactions with a ranked list as a dynamic system instead of one-step click prediction, alleviating the exposure bias problem. Finally, we minimize the JS divergence through adversarial training and learn a stable distribution of click sequences, which makes AICM generalize well across different distributions of ranked lists. A theoretical analysis has indicated that AICM reduces the exposure bias from O(T2) to O(T). Our studies on a public web search dataset show that AICM not only outperforms state-of-the-art models in traditional click metrics but also achieves superior performance in addressing the exposure bias and recovering the underlying patterns of click sequences.