# IntroLM: Introspective Language Models via Prefilling-Time Self-Evaluation

arXiv: https://arxiv.org/abs/2601.03511 · HTML: https://mlsanity.com/paper/2601.03511/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 29 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [Learning to Route LLMs with Confidence Tokens](https://mlsanity.com/paper/2410.13284/) (2024)
- [BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute](https://mlsanity.com/paper/2506.22716/) (2025)

## Built on by (most cited first, 3 of 3)

- [RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving](https://mlsanity.com/paper/2604.10907/) (2026)
- [HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment](https://mlsanity.com/paper/2609.38006/) (2026)
- [Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing](https://mlsanity.com/paper/2610.06216/) (2026)

## Abstract (arXiv)

A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-quality output for a given query. Existing approaches rely on external classifiers, most commonly BERT based models, which suffer from limited context windows, constrained representational capacity, and additional computational overhead. We propose IntroLM, a method that enables causal language models to predict their own output quality during the prefilling phase without affecting generation using introspective tokens. By introducing token conditional LoRA that activates only for the introspective token, the model learns to predict the output quality for a given query while preserving the original backbone behavior and avoiding external evaluators. On question answering benchmarks, IntroLM applied to Qwen3 8B achieves a ROC AUC of 90 precent for success prediction, outperforming a DeBERTa classifier by 14 precent. When integrated into multi model routing systems, IntroLM achieves superior cost performance tradeoffs, reducing latency by up to 33 precent and large model usage by up to 50 precent at matched reliability.