# Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation

arXiv: https://arxiv.org/abs/2204.01171 · HTML: https://mlsanity.com/paper/2204.01171/

## Key facts

- Cited by 108 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 3 Apr 2022.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [An Actor-Critic Algorithm for Sequence Prediction](https://mlsanity.com/paper/1607.07086/) (2016)
- [On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation](https://mlsanity.com/paper/2005.03642/) (2020)
- [Bridging the Gap between Training and Inference for Neural Machine Translation](https://mlsanity.com/paper/1906.02448/) (2019)
- [Generalization in Generation: A closer look at Exposure Bias](https://mlsanity.com/paper/1910.00292/) (2019)
- [Minimum Risk Training for Neural Machine Translation](https://mlsanity.com/paper/1512.02433/) (2015)
- [Towards an Automatic Turing Test: Learning to Evaluate Dialogue Responses](https://mlsanity.com/paper/1708.07149/) (2017)
- [Residual Energy-Based Models for Text Generation](https://mlsanity.com/paper/2004.11714/) (2020)
- [Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation](https://mlsanity.com/paper/1908.04942/) (2019)
- [Composable Planning with Attributes](https://mlsanity.com/paper/1803.00512/) (2018)
- [SEARNN: Training RNNs with Global-Local Losses](https://mlsanity.com/paper/1706.04499/) (2017)
- [An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation](https://mlsanity.com/paper/1908.10835/) (2019)
- [Teacher-Student Training for Robust Tacotron-based TTS](https://mlsanity.com/paper/1911.02839/) (2019)

## Built on by (most cited first, 30 of 108)

- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [How Language Model Hallucinations Can Snowball](https://mlsanity.com/paper/2305.13534/) (2023)
- [Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization](https://mlsanity.com/paper/2210.01241/) (2022)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [DistiLLM: Towards Streamlined Distillation for Large Language Models](https://mlsanity.com/paper/2402.03898/) (2024)
- [Stream of Search (SoS): Learning to Search in Language](https://mlsanity.com/paper/2404.03683/) (2024)
- [MiniLLM: On-Policy Distillation of Large Language Models](https://mlsanity.com/paper/2306.08543/) (2023)
- [Deductive Verification of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2306.03872/) (2023)
- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)
- [Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation](https://mlsanity.com/paper/2502.20388/) (2025)
- [Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking](https://mlsanity.com/paper/2402.09369/) (2024)
- [Stable On-Policy Distillation through Adaptive Target Reformulation](https://mlsanity.com/paper/2601.07155/) (2026)
- [Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning](https://mlsanity.com/paper/2308.12219/) (2023)
- [Reward Gaming in Conditional Text Generation](https://mlsanity.com/paper/2211.08714/) (2022)
- [CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming](https://mlsanity.com/paper/2410.02677/) (2024)
- [Tailoring Language Generation Models under Total Variation Distance](https://mlsanity.com/paper/2302.13344/) (2023)
- [Frequency Autoregressive Image Generation with Continuous Tokens](https://mlsanity.com/paper/2503.05305/) (2025)
- [On the Position Bias of On-Policy Distillation](https://mlsanity.com/paper/2606.22600/) (2026)
- [PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning](https://mlsanity.com/paper/2402.12842/) (2024)
- [AdvPrefix: An Objective for Nuanced LLM Jailbreaks](https://mlsanity.com/paper/2412.10321/) (2024)
- [SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs](https://mlsanity.com/paper/2510.24021/) (2025)
- [PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in Control](https://mlsanity.com/paper/2402.10450/) (2024)
- [Imitating Language via Scalable Inverse Reinforcement Learning](https://mlsanity.com/paper/2409.01369/) (2024)
- [Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation](https://mlsanity.com/paper/2508.03334/) (2025)
- [Self-Improving Robust Preference Optimization](https://mlsanity.com/paper/2406.01660/) (2024)
- [HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration](https://mlsanity.com/paper/2410.01723/) (2024)
- [A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training](https://mlsanity.com/paper/2305.02031/) (2023)
- [Understanding and Bridging the Modality Gap for Speech Translation](https://mlsanity.com/paper/2305.08706/) (2023)
- [Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries](https://mlsanity.com/paper/2510.14751/) (2025)

## Abstract (arXiv)

Current language generation models suffer from issues such as repetition, incoherence, and hallucinations. An often-repeated hypothesis is that this brittleness of generation models is caused by the training and the generation procedure mismatch, also referred to as exposure bias. In this paper, we verify this hypothesis by analyzing exposure bias from an imitation learning perspective. We show that exposure bias leads to an accumulation of errors, analyze why perplexity fails to capture this accumulation, and empirically show that this accumulation results in poor generation quality. Source code to reproduce these experiments is available at https://github.com/kushalarora/quantifying_exposure_bias