# Self-Consistency Falls Short! The Adverse Effects of Positional Bias on Long-Context Problems

arXiv: https://arxiv.org/abs/2411.01101 · HTML: https://mlsanity.com/paper/2411.01101/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 37 of its 52 references that are in the map.
- First posted on arXiv 2 Nov 2024.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 30 of 37)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [True Few-Shot Learning with Language Models](https://mlsanity.com/paper/2105.11447/) (2021)
- [Mathematical Capabilities of ChatGPT](https://mlsanity.com/paper/2301.13867/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [QuALITY: Question Answering with Long Input Texts, Yes!](https://mlsanity.com/paper/2112.08608/) (2021)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding](https://mlsanity.com/paper/2305.14196/) (2023)
- [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://mlsanity.com/paper/2201.03533/) (2022)
- [HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly](https://mlsanity.com/paper/2410.02694/) (2024)
- [Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization](https://mlsanity.com/paper/2406.16008/) (2024)

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

- [APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI](https://mlsanity.com/paper/2604.14362/) (2026)
- [Agentic Test-Time Scaling for WebAgents](https://mlsanity.com/paper/2602.12276/) (2026)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [GOLD PANNING: Strategic Context Shuffling for Needle-in-Haystack Reasoning](https://mlsanity.com/paper/2510.09770/) (2025)
- [Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge](https://mlsanity.com/paper/2608.12218/) (2026)
- [The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents](https://mlsanity.com/paper/2609.01852/) (2026)
- [Crystal: Characterizing Relative Impact of Scholarly Publications](https://mlsanity.com/paper/2603.26791/) (2026)

## Abstract (arXiv)

Self-consistency (SC) improves the performance of large language models (LLMs) across various tasks and domains that involve short content. However, does this support its effectiveness for long-context problems? We challenge the assumption that SC's benefits generalize to long-context settings, where LLMs often struggle with position bias, the systematic over-reliance on specific context regions-which hinders their ability to utilize information effectively from all parts of their context. Through comprehensive experimentation with varying state-of-the-art models, tasks, and SC formulations, we find that SC not only fails to improve but actively degrades performance on long-context tasks. This degradation is driven by persistent position bias, which worsens with longer context lengths and smaller model sizes but remains invariant to prompt format or task type. Unlike short-context tasks, where SC diversifies reasoning paths, long-context SC amplifies positional errors. These comprehensive results provide valuable insight into the limitations of current LLMs in long-context understanding and highlight the need for more sophisticated approaches.