# Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters

arXiv: https://arxiv.org/abs/2510.25860 · HTML: https://mlsanity.com/paper/2510.25860/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 14 of its 54 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 14 of 14)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [A Systematic Survey of Automatic Prompt Optimization Techniques](https://mlsanity.com/paper/2502.16923/) (2025)
- [Fino1: On the Transferability of Reasoning-Enhanced LLMs and Reinforcement Learning to Finance](https://mlsanity.com/paper/2502.08127/) (2025)
- [Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training](https://mlsanity.com/paper/2502.11191/) (2025)
- [Evaluating Creative Short Story Generation in Humans and Large Language Models](https://mlsanity.com/paper/2411.02316/) (2024)
- [Potential and Perils of Large Language Models as Judges of Unstructured Textual Data](https://mlsanity.com/paper/2501.08167/) (2025)
- [An LLM-as-Judge Metric for Bridging the Gap with Human Evaluation in SE Tasks](https://mlsanity.com/paper/2505.20854/) (2025)

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

- [Margin-Adaptive Confidence Ranking for Reliable LLM Judgement](https://mlsanity.com/paper/2605.15416/) (2026)
- [RADAR: Rubric-Aware Dependency and Redundancy Analysis for LLM-as-Judge Evaluation](https://mlsanity.com/paper/2608.01810/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as raters for evaluation tasks. However, their reliability is often limited for subjective tasks, when human judgments involve subtle reasoning beyond annotation labels. Thinking traces, the reasoning behind a judgment, are highly informative but challenging to collect and curate. We present a human-LLM collaborative framework to infer thinking traces from label-only annotations. The proposed framework uses a simple and effective rejection sampling method to reconstruct these traces at scale. These inferred thinking traces are applied to two complementary tasks: (1) fine-tuning open LLM raters; and (2) synthesizing clearer annotation guidelines for proprietary LLM raters. Across multiple datasets, our methods lead to significantly improved LLM-human agreement. Additionally, the refined annotation guidelines increase agreement among different LLM models. These results suggest that LLMs can serve as practical proxies for otherwise unrevealed human thinking traces, enabling label-only corpora to be extended into thinking-trace-augmented resources that enhance the reliability of LLM raters.