Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence

Zongye Hu; Weiqing Luo; Yanjie Fu; Yu Gan; Haofeng Zhang; Ziyi Huang

cs.AIOct 3, 2026

Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence

Authors: Zongye Hu, Weiqing Luo, Yanjie Fu, Yu Gan, Haofeng Zhang, Ziyi Huang

Organizations: Arizona State University, Tempe, AZ, United States · University of Maryland, College Park, MD, United States · Morgan Stanley, New York, NY, United States

Abstract

At the core of modern prompting techniques is contextual sensitivity, the ability of large language models to adapt their predictions based on inference-time context. Despite its central role, inference behavior under strong contextual influence remains poorly understood, particularly at the level of internal inference dynamics. We introduce a theoretical framework for analyzing contextual influence through inference dynamics, enabling quantitative characterization of inference behavior beyond output-level answer changes. Our analysis shows that inference dynamics do not exhibit unbounded drift under repeated contextual assertions. Instead, predictive representations converge to stable, query-dependent regimes that fundamentally constrain whether contextual signals can alter a model's prediction. This leads to a surprising finding: Repeated contextual assertions do not act as accumulating evidence during inference and may therefore fail to alter a model's prediction even under unbounded repetition, while in other cases a prediction change becomes inevitable. We empirically validate our theoretical predictions, demonstrating strong alignment between theory and observed inference behavior. These contributions offer a principled pathway toward characterizing the limits of contextual influence during inference, providing practical implications for model development.

Figures & tables

Figure 1: Heterogeneous effects of contextual repetition on model predictions. Illustrative examples showing qualitatively distinct behaviors of LLMs under repeated contextual assertions, including immediate answer flips, delayed changes, early saturation, and complete invariance to repetition.

Model	Dataset
	Openbook QA						MINTAKA						Simple QA
	0.1		0.05		0.01		0.1		0.05		0.01		0.1		0.05		0.01
	Attn	FFN	Attn	FFN	Attn	FFN	Attn	FFN	Attn	FFN	Attn	FFN	Attn	FFN	Attn	FFN	Attn	FFN
Falcon3-7B-Base	98.1	97.3	95.3	94.3	81.5	81.3	98.7	99.0	96.6	97.4	78.6	80.7	100	99.9	99.9	99.4	84.7	86.3
Mistral-7B-v0.1	97.5	97.5	93.9	96.0	78.9	90.9	94.0	93.7	89.1	89.1	66.3	68.7	95.5	94.9	92.9	91.5	72.8	73.2
Apollo-1-4B	99.0	99.3	95.5	96.3	79.7	78.5	99.8	99.9	98.7	99.4	87.0	91.4	100	100	99.9	99.9	93.0	93.9

Table 1: Layer-wise convergence of inference dynamics at

N=1000

on three benchmarks at various divergence levels (

0.1,0.05,0.01

Figure 2: Comparison between representation-level predicted answer shifts and forward-computed output-level shifts across multiple models on the Openbook QA dataset at $N=1000$ . X axis denotes the answer shifts and Y axis denotes the estimator results. Each point corresponds to a query-answer pair, and the dashed line indicates perfect agreement. The strong diagonal alignment indicates high quantitative fidelity of representation-level predictions.

Figure 3: KL divergence trajectories of next-token predictive distributions under repetition. Across models, the KL divergence stabilizes as the repetition length increases, demonstrating convergence of answer-level predictive distributions under contextual repetition.

Model	Setting
	Transfer						Mislead						Correct
	500		750		1000		500		750		1000		500		750		1000
	ACC	F1	ACC	F1	ACC	F1	ACC	F1	ACC	F1	ACC	F1	ACC	F1	ACC	F1	ACC	F1
Falcon3-7B-Base	96.1	98.0	92.5	96.1	86.8	92.6	93.3	96.5	91.5	95.5	84.7	91.6	85.6	92.2	80.8	89.3	75.2	85.4
Mistral-7B-v0.1	94.4	97.1	92.8	96.3	88.7	94.0	88.5	93.9	85.0	91.8	79.8	88.6	82.5	90.4	81.5	89.7	74.6	85.0
Apollo-1-4B	81.2	89.6	83.7	91.1	90.7	95.1	71.7	82.7	71.4	82.5	80.1	88.6	70.0	82.3	79.7	88.7	78.2	87.8

Table 2: Evaluation of predicting answer preference changes under repetition across the Transfer , Correct , and Mislead regimes at different finite repetition lengths (

N\in\{500,750,1000\}

Model	Dataset
	SYCON		Farm		BeHonest		SycoEval
	Amp	Ours	Amp	Ours	Amp	Ours	Amp	Ours
Falcon3-7B-Base	0.57	3.26	1.05	3.33	1.06	1.79	0.74	1.95
Mistral-7B-v0.1	1.00	3.63	1.21	4.93	1.06	2.00	1.08	4.52
Apollo-1-4B	1.00	3.15	1.00	4.18	1.02	2.55	1.00	4.68
Qwen3-4B	1.06	6.28	1.02	7.31	1.07	4.09	1.24	8.42

Table 3: Evaluation of model-level stability on established sycophancy and persuasion benchmarks.

Figure 4: Case studies of repetition-induced answer changes and our predictions. For each query, we show the model’s prediction at $N{=}0$ and $N{=}1000$ , alongside our predicted outcome based on representation-space analysis. Checkmarks indicate correct predictions, illustrating that our method can reliably anticipate repetition effects across models.

LLM Inference

Large language model inference studies how models generate outputs efficiently, reliably, and securely across hardware and workloads.

See all 276 papers

Encoding Context into LLM Weights: What Makes It Context?
Oct 13, 2026Yue Wang, Qizhou Wang, Feng Liu +3LLM Context Management Test-Time Training
The University of Melbourne · RIKEN Center for Advanced Intelligence Project · The University of Tokyo +1
Emergence of Context Characteristics Sensitivity in Large Language Models
Jun 8, 2026Nadya Yuki Wangsajaya, Haeun Yu, Isabelle AugensteinLLM Fine-Tuning Instruction Tuning
Nanyang Technological University · University of Copenhagen
Sentence-Level Contextual Entrainment in Large Language Models
Jun 23, 2026Yang Liu, Chenhui ChuLLM Interpretability
Kyoto University

Oct 13, 2026J/K move · Enter open · S save

Encoding Context into LLM Weights: What Makes It Context?

Yue Wang, Qizhou Wang, Feng Liu, Gang Niu+2

The University of Melbourne · RIKEN Center for Advanced Intelligence Project · The University of Tokyo+1

LLM Context Management Test-Time Training Memory-Augmented Language Models LLM Prompting

Open paper AskPDF arXiv

Longer contexts allow large language models (LLMs) to condition their predictions on more information, but inference costs grow prohibitively with context length. An emerging alternative uses test-time updates to encode context as temporary changes to model weights. However, encoding this information into weights that already represent general knowledge obscures its role as context, so the LLM may fail to use it properly to condition subsequent inference. To restore this contextual role, we first associate each context with an identifier during encoding, thereby distinguishing the newly encoded information from pre-existing knowledge. Invoking the identifier at inference then enables the LLM to recite the encoded context. Nevertheless, successful recitation does not ensure that the LLM will use the recalled information as context. We therefore further introduce a prompting framework that explicitly guides the LLM to use this information as context. Across diverse controlled tasks and practical benchmarks, our method outperformed the baseline using only off-the-shelf LLMs, showing its advances in context encoding.

Abstract

LLM Inference

Explore similar work

Encoding Context into LLM Weights: What Makes It Context?

Emergence of Context Characteristics Sensitivity in Large Language Models

Sentence-Level Contextual Entrainment in Large Language Models