Evaluating the Sensitivity of LLMs to Prior Context

• URL: http://arxiv.org/abs/2506.00069v1
• Date: Thu, 29 May 2025 16:09:32 GMT
• Title: Evaluating the Sensitivity of LLMs to Prior Context
• Abstract summary: Large language models (LLMs) are increasingly deployed in multi-turn dialogue and other sustained interactive scenarios.<n>We introduce a novel set of benchmarks that vary the volume and nature of prior context to measure sensitivity to contextual variations.<n>Our findings reveal that LLM performance on multiple-choice questions can degrade dramatically in multi-turn interactions.
• Score: 2.377922603550519
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language models (LLMs) are increasingly deployed in multi-turn dialogue and other sustained interactive scenarios, it is essential to understand how extended context affects their performance. Popular benchmarks, focusing primarily on single-turn question answering (QA) tasks, fail to capture the effects of multi-turn exchanges. To address this gap, we introduce a novel set of benchmarks that systematically vary the volume and nature of prior context. We evaluate multiple conventional LLMs, including GPT, Claude, and Gemini, across these benchmarks to measure their sensitivity to contextual variations. Our findings reveal that LLM performance on multiple-choice questions can degrade dramatically in multi-turn interactions, with performance drops as large as 73% for certain models. Even highly capable models such as GPT-4o exhibit up to a 32% decrease in accuracy. Notably, the relative performance of larger versus smaller models is not always predictable. Moreover, the strategic placement of the task description within the context can substantially mitigate performance drops, improving the accuracy by as much as a factor of 3.5. These findings underscore the need for robust strategies to design, evaluate, and mitigate context-related sensitivity in LLMs.

Related papers

• Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation [2.221515121005437]
  Several studies claim better performance with more sophisticated prompting techniques, but do not provide a comprehensive evaluation.<n>We address this gap through a comprehensive empirical study of 8 prompting techniques across 10 multiple-choice question answering (MCQA) datasets.<n>Our findings reveal a striking paradox that baseline prompting consistently outperforms complex reasoning techniques on various benchmarks.
  arXiv  Detail & Related papers  (2026-05-07T21:11:51Z)
• Does Tone Change the Answer? Evaluating Prompt Politeness Effects on Modern LLMs: GPT, Gemini, LLaMA [0.6263481844384227]
  This work proposes a systematic evaluation framework to examine how interaction tone affects model accuracy.<n>We apply this framework to three recently released and widely available large language models: GPT-4o mini (OpenAI), Gemini 2.0 Flash (Google DeepMind), and Llama 4 Scout (Meta)<n>Our results show that tone sensitivity is both model-dependent and domain-specific. Neutral or Very Friendly prompts generally yield higher accuracy than Very Rude prompts, but statistically significant effects appear only in a subset of Humanities tasks.
  arXiv  Detail & Related papers  (2025-12-14T19:25:20Z)
• Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning [49.559151128219725]
  Large language models (LLMs) have shown great promise in the medical domain, achieving strong performance on several benchmarks.<n>However, they continue to underperform in real-world medical scenarios, which often demand stronger context-awareness.<n>We propose Multifaceted Self-Refinement (MuSeR), a data-driven approach that enhances LLMs' context-awareness along three key facets.
  arXiv  Detail & Related papers  (2025-11-13T08:13:23Z)
• Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL [64.3268313484078]
  Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare.<n>Their ability to produce deceptive outputs, whether intentionally or inadvertently, poses significant safety concerns.<n>We investigate the extent to which LLMs engage in deception within dialogue, and propose the belief misalignment metric to quantify deception.
  arXiv  Detail & Related papers  (2025-10-16T05:29:36Z)
• ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models [9.509429747913519]
  Large Language Models (LLMs) suffer significant performance degradation in multi-turn conversations when information is presented incrementally.<n>We introduce ERGO, which quantifies internal uncertainty via Shannon entropy over next token distributions.<n> ERGO embraces variability in language and modeling, representing and responding to uncertainty.
  arXiv  Detail & Related papers  (2025-10-15T20:33:08Z)
• Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? [81.49470136653665]
  We evaluate the robustness and expressiveness of value representations across three widely used probing strategies.<n>We show that the demographic context has little effect on the free-text generation, and the models' values only weakly correlate with their preference for value-based actions.
  arXiv  Detail & Related papers  (2025-07-17T18:56:41Z)
• The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs [40.35884943268004]
  We show that for very long sequences, larger and highly sparse models are preferable to smaller and dense ones.<n>There is no clear strategy that performs best across tasks and phases, with different units of sparsification or budget adaptivity needed for different scenarios.<n>We introduce and validate novel scaling laws specifically tailored for sparse attention, providing evidence that our findings are likely to hold true beyond our range of experiments.
  arXiv  Detail & Related papers  (2025-04-24T17:39:25Z)
• Meta-Evaluating Local LLMs: Rethinking Performance Metrics for Serious Games [3.725822359130832]
  Large Language Models (LLMs) are increasingly being explored as evaluators in serious games.<n>This study investigates the reliability of five small-scale LLMs when assessing player responses in textitEn-join, a game that simulates decision-making within energy communities.<n>Our results highlight the strengths and limitations of each model, revealing trade-offs between sensitivity, specificity, and overall performance.
  arXiv  Detail & Related papers  (2025-04-13T10:46:13Z)
• Out of Style: RAG's Fragility to Linguistic Variation [29.59506089890902]
  User queries exhibit greater linguistic variations and can trigger cascading errors across interdependent RAG components.<n>We analyze how varying four linguistic dimensions (formality, readability, politeness, and grammatical correctness) impact RAG performance.
  arXiv  Detail & Related papers  (2025-04-11T03:30:26Z)
• Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleon [11.753349115726952]
  Large language models (LLMs) often appear to excel on public benchmarks, but these high scores may mask an overreliance on dataset-specific surface cues.<n>We introduce the Chameleon Benchmark Overfit Detector (C-BOD), a meta-evaluation framework that distorts benchmark prompts.<n>By rephrasing inputs while preserving semantic content and labels, C-BOD exposes whether a model's performance is driven by memorized patterns.
  arXiv  Detail & Related papers  (2025-02-11T10:43:36Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• Exploring Knowledge Boundaries in Large Language Models for Retrieval Judgment [56.87031484108484]
  Large Language Models (LLMs) are increasingly recognized for their practical applications. Retrieval-Augmented Generation (RAG) tackles this challenge and has shown a significant impact on LLMs. By minimizing retrieval requests that yield neutral or harmful results, we can effectively reduce both time and computational costs.
  arXiv  Detail & Related papers  (2024-11-09T15:12:28Z)
• MM-R$^3$: On (In-)Consistency of Vision-Language Models (VLMs) [26.475993408532304]
  We analyze performance of SoTA Vision Language Models on three tasks: Question Rephrasing, Image Restyling, and Context Reasoning.<n>Our analysis reveals that consistency does not always align with accuracy, indicating that models with higher accuracy are not necessarily more consistent, and vice versa.<n>We propose a simple yet effective mitigation strategy in the form of an adapter module trained to minimize inconsistency across prompts.
  arXiv  Detail & Related papers  (2024-10-07T06:36:55Z)
• MMRel: A Relation Understanding Benchmark in the MLLM Era [72.95901753186227]
  Multi-Modal Relation Understanding (MMRel) is a benchmark that features large-scale, high-quality, and diverse data on inter-object relations. MMRel is ideal for evaluating MLLMs on relation understanding, as well as for fine-tuning MLLMs to enhance relation comprehension capability.
  arXiv  Detail & Related papers  (2024-06-13T13:51:59Z)
• On the Worst Prompt Performance of Large Language Models [93.13542053835542]
  Performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts. We introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries. Experiments on RobustAlpacaEval with ChatGPT and six open-source LLMs from the Llama, Mistral, and Gemma families uncover substantial variability in model performance.
  arXiv  Detail & Related papers  (2024-06-08T13:40:38Z)
• Cutting Through the Noise: Boosting LLM Performance on Math Word Problems [52.99006895757801]
  Large Language Models excel at solving math word problems, but struggle with real-world problems containing irrelevant information.<n>We propose a prompting framework that generates adversarial variants of MWPs by adding irrelevant variables.<n> Fine-tuning on adversarial training instances improves performance on adversarial MWPs by 8%.
  arXiv  Detail & Related papers  (2024-05-30T18:07:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.