# Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short

arXiv: https://arxiv.org/abs/2510.08985 · HTML: https://mlsanity.com/paper/2510.08985/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 16 of 16)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://mlsanity.com/paper/2309.15088/) (2023)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning](https://mlsanity.com/paper/2503.06034/) (2025)
- [ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability](https://mlsanity.com/paper/2508.07050/) (2025)
- [JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking](https://mlsanity.com/paper/2411.00142/) (2024)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](https://mlsanity.com/paper/2505.20046/) (2025)
- [ReasoningRank: Teaching Student Models to Rank through Reasoning-Based Knowledge Distillation](https://mlsanity.com/paper/2410.05168/) (2024)
- [MultiConIR: Towards multi-condition Information Retrieval](https://mlsanity.com/paper/2503.08046/) (2025)
- [Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?](https://mlsanity.com/paper/2505.16886/) (2025)
- [TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking](https://mlsanity.com/paper/2508.09539/) (2025)
- [From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval](https://mlsanity.com/paper/2505.23059/) (2025)

## Built on by (most cited first, 7 of 7)

- [The Embedder's Dilemma: LLMs Are Better, but at What Cost?](https://mlsanity.com/paper/2608.12875/) (2026)
- [Beyond Global Similarity: Towards Fine-Grained, Multi-Condition Multimodal Retrieval](https://mlsanity.com/paper/2603.01082/) (2026)
- [Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval](https://mlsanity.com/paper/2604.23734/) (2026)
- [CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free Scoring](https://mlsanity.com/paper/2606.11700/) (2026)
- [Tool-Adaptive LLM Reranker](https://mlsanity.com/paper/2607.10555/) (2026)
- [TabRank: Chain-of-Thought Distillation for Table Re-Rankers](https://mlsanity.com/paper/2607.25182/) (2026)
- [Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers](https://mlsanity.com/paper/2608.26762/) (2026)

## Abstract (arXiv)

Document reranking is a key component in information retrieval (IR), aimed at refining initial retrieval results to improve ranking quality for downstream tasks. Recent studies--motivated by large reasoning models (LRMs)--have begun incorporating explicit chain-of-thought (CoT) reasoning into LLM-based rerankers. However, the effectiveness of such reasoning for ranking tasks remains underexplored. In this work, we present the first systematic study of reasoning in reranking across both pointwise and listwise settings, under both supervised fine-tuning and reinforcement learning. Using diverse benchmarks, including reasoning-intensive datasets (BRIGHT) and standard IR benchmarks (BEIR), we find that reasoning-augmented rerankers consistently underperform their direct counterparts that predict rankings without CoT, despite substantially higher inference costs. Our analysis reveals three core limitations: (i) in pointwise rerankers, reasoning breaks calibration and biases models toward the positive class, raising TPR but lowering TNR, which inflates false positives and degrades ranking in negative-dominant pools; (ii) in listwise rerankers, reasoning improves in-domain fit but increases variance and fails to generalize out-of-domain, even when reinforcement learning shortens rationales; and (iii) overall, directly fine-tuned rerankers remain more stable, effective, and robust. These findings challenge the assumption that explicit reasoning is universally beneficial for reranking. We conclude by highlighting future directions, including calibration-aware scoring for pointwise rerankers and the design of concise, targeted reasoning strategies to mitigate overfitting and overthinking in listwise rerankers.