# Predicting Through Generation: Why Generation Is Better for Prediction

arXiv: https://arxiv.org/abs/2502.17817 · HTML: https://mlsanity.com/paper/2502.17817/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 60 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [LoRA-FA: Efficient and Effective Low Rank Representation Fine-tuning](https://mlsanity.com/paper/2308.03303/) (2023)
- [Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://mlsanity.com/paper/2210.12810/) (2022)
- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Mixture-of-Subspaces in Low-Rank Adaptation](https://mlsanity.com/paper/2406.11909/) (2024)
- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)

## Built on by (most cited first, 2 of 2)

- [FlowNIB: An Information Bottleneck Analysis of Bidirectional vs. Unidirectional Language Models](https://mlsanity.com/paper/2506.00859/) (2025)
- [LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning](https://mlsanity.com/paper/2604.02338/) (2026)

## Abstract (arXiv)

This paper argues that generating output tokens is more effective than using pooled representations for prediction tasks because token-level generation retains more mutual information. Since LLMs are trained on massive text corpora using next-token prediction, generation aligns naturally with their learned behavior. Using the Data Processing Inequality (DPI), we provide both theoretical and empirical evidence supporting this claim. However, autoregressive models face two key challenges when used for prediction: (1) exposure bias, where the model sees ground truth tokens during training but relies on its own predictions during inference, leading to errors, and (2) format mismatch, where discrete tokens do not always align with the tasks required output structure. To address these challenges, we introduce PredGen(Predicting Through Generating), an end to end framework that (i) uses scheduled sampling to reduce exposure bias, and (ii) introduces a task adapter to convert the generated tokens into structured outputs. Additionally, we introduce Writer-Director Alignment Loss (WDAL), which ensures consistency between token generation and final task predictions, improving both text coherence and numerical accuracy. We evaluate PredGen on multiple classification and regression benchmarks. Our results show that PredGen consistently outperforms standard baselines, demonstrating its effectiveness in structured prediction tasks.