# Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration

arXiv: https://arxiv.org/abs/2604.10150 · HTML: https://mlsanity.com/paper/2604.10150/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 53 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Builds on (most cited first, 30 of 42)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization](https://mlsanity.com/paper/2406.16008/) (2024)
- [Rank1: Test-Time Compute for Reranking in Information Retrieval](https://mlsanity.com/paper/2502.18418/) (2025)
- [FIRST: Faster Improved Listwise Reranking with Single Token Decoding](https://mlsanity.com/paper/2406.15657/) (2024)
- [Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding](https://mlsanity.com/paper/2405.02750/) (2024)
- [Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers](https://mlsanity.com/paper/2410.02642/) (2024)
- [ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval](https://mlsanity.com/paper/2402.15838/) (2024)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [Overview of the TREC 2022 deep learning track](https://mlsanity.com/paper/2507.10865/) (2025)
- [Exploring User Retrieval Integration towards Large Language Models for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2406.03085/) (2024)
- [Entropy-Based Decoding for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2406.17519/) (2024)
- [RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery](https://mlsanity.com/paper/2503.00751/) (2025)
- [Overview of the TREC 2021 deep learning track](https://mlsanity.com/paper/2507.08191/) (2025)
- [From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL](https://mlsanity.com/paper/2311.06595/) (2023)
- [Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent](https://mlsanity.com/paper/2506.23485/) (2025)
- [Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation](https://mlsanity.com/paper/2402.14874/) (2024)
- [LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking](https://mlsanity.com/paper/2406.00231/) (2024)
- [Generative Large Recommendation Models: Emerging Trends in LLMs for Recommendation](https://mlsanity.com/paper/2502.13783/) (2025)
- [Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model](https://mlsanity.com/paper/2504.16454/) (2025)
- [CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering](https://mlsanity.com/paper/2507.04756/) (2025)
- [FuXi-α: Scaling Recommendation Model with Feature Interaction Enhanced Transformer](https://mlsanity.com/paper/2502.03036/) (2025)
- [Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy](https://mlsanity.com/paper/2412.00430/) (2024)
- [Overview of the TREC 2023 deep learning track](https://mlsanity.com/paper/2507.08890/) (2025)
- [SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment](https://mlsanity.com/paper/2509.03934/) (2025)

## Built on by (most cited first, 4 of 4)

- [IE as Cache: Information Extraction Enhanced Agentic Reasoning](https://mlsanity.com/paper/2604.14930/) (2026)
- [AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs](https://mlsanity.com/paper/2608.26004/) (2026)
- [Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking](https://mlsanity.com/paper/2604.15621/) (2026)
- [Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers](https://mlsanity.com/paper/2608.26762/) (2026)

## Abstract (arXiv)

Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural sensitivity to input order independent of relevance. Existing mitigations present a dilemma: inference-time aggregation incurs prohibitive latency, while training-based methods often fail to eradicate ingrained priors, particularly in compact models. To resolve this dilemma, we propose CapCal (Content-Agnostic Probability Calibration), a training-free framework that mechanically decouples positional bias from ranking decisions. By estimating the bias distribution via content-free placeholders, CapCal rectifies output logits through an entropy-adaptive contrastive mechanism. Evaluations across 10 benchmarks confirm that CapCal achieves superior performance among training-free methods while preserving single-pass efficiency. Notably, it unlocks the latent potential of lightweight models (e.g., 0.6B), delivering absolute NDCG gains exceeding 10 points and outperforming both permutation-based aggregation and data-augmentation baselines.