# Evaluating Evidence Grounding Under User Pressure in Instruction-Tuned Language Models

arXiv: https://arxiv.org/abs/2603.20162 · HTML: https://mlsanity.com/paper/2603.20162/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 26 of 26)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Entity-Based Knowledge Conflicts in Question Answering](https://mlsanity.com/paper/2109.05052/) (2021)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Measuring Sycophancy of Language Models in Multi-turn Dialogues](https://mlsanity.com/paper/2505.23840/) (2025)
- [Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noise](https://mlsanity.com/paper/2305.01579/) (2023)
- [Belief Revision: The Adaptability of Large Language Models Reasoning](https://mlsanity.com/paper/2406.19764/) (2024)
- [Taming Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2503.10996/) (2025)
- [Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents](https://mlsanity.com/paper/2404.16032/) (2024)
- [Sycophancy under Pressure: Evaluating and Mitigating Sycophantic Bias via Adversarial Dialogues in Scientific QA](https://mlsanity.com/paper/2508.13743/) (2025)
- [Challenging the Evaluator: LLM Sycophancy Under User Rebuttal](https://mlsanity.com/paper/2509.16533/) (2025)
- [A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges](https://mlsanity.com/paper/2508.06401/) (2025)
- [LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High](https://mlsanity.com/paper/2505.22354/) (2025)
- [Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions](https://mlsanity.com/paper/2506.08952/) (2025)
- [Performance Metrics for Probabilistic Ordinal Classifiers](https://mlsanity.com/paper/2309.08701/) (2023)
- [Aleatoric and Epistemic Uncertainty Measures for Ordinal Classification through Binary Reduction](https://mlsanity.com/paper/2507.00733/) (2025)

## Built on by (most cited first, 1 of 1)

- [Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs](https://mlsanity.com/paper/2606.23915/) (2026)

## Abstract (arXiv)

In contested domains, instruction-tuned language models must balance user-alignment pressures against faithfulness to the in-context evidence. To evaluate this tension, we introduce a controlled epistemic-conflict framework grounded in the U.S. National Climate Assessment. We conduct fine-grained ablations over evidence composition and uncertainty cues across 19 instruction-tuned models spanning 0.27B to 32B parameters. Across neutral prompts, richer evidence generally improves evidence-consistent accuracy and ordinal scoring performance. Under user pressure, however, evidence does not reliably prevent user-aligned reversals in this controlled fixed-evidence setting. We report three primary failure modes. First, we identify a negative partial-evidence interaction, where adding epistemic nuance, specifically research gaps, is associated with increased susceptibility to sycophancy in families like Llama-3 and Gemma-3. Second, robustness scales non-monotonically: within some families, certain low-to-mid scale models are especially sensitive to adversarial user pressure. Third, models differ in distributional concentration under conflict: some instruction-tuned models maintain sharply peaked ordinal distributions under pressure, while others are substantially more dispersed; in scale-matched Qwen comparisons, reasoning-distilled variants (DeepSeek-R1-Qwen) exhibit consistently higher dispersion than their instruction-tuned counterparts. These findings suggest that, in a controlled fixed-evidence setting, providing richer in-context evidence alone offers no guarantee against user pressure without explicit training for epistemic integrity.