Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models

Victor De Lima; Jiqun Liu; Grace Hui Yang

cs.CYFeb 17, 2026

Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models

Authors: Victor De Lima, Jiqun Liu, Grace Hui Yang

Organizations: Georgetown InfoSense Washington, D.C., USA · University of Oklahoma Norman, Oklahoma, USA

Abstract

AI systems increasingly shape how individuals access and evaluate information, intensifying concerns about misinformation. Computational simulation offers a controlled complement to direct empirical study, with fine-tuned LLMs enabling powerful agent-based simulations. However, fine-tuning often induces broad behavioral shifts including bias drift, degenerate heuristics, and changes in baseline task behavior, which undermine experimental validity. The central challenge is inducing localized decision shifts while preserving the model's aggregate behavior outside the targeted intervention. We study this through a stability analysis of supervised fine-tuning, attenuating loss on selected training slices to shift false-claim acceptance. We introduce FrameRef, a large-scale dataset of semantically equivalent claims with controlled surface framings across five dimensions (Authoritative, Consensus, Emotional, Sensationalist, Prestige), with human validation confirming systematic framing effects on claim acceptance. We present a methodology for identifying model-specific stability regimes in which targeted error shifts can be induced while preserving aggregate accuracy and calibration, and demonstrate its application to selected language models. A sequential exposure task over FrameRef shows that small framing-conditioned shifts compound into substantially different cumulative outcomes under feedback, but largely disappear when feedback is removed, confirming that interventions modify specific decision tendencies rather than global performance. We release code, LoRA adapters, and data at https://github.com/infosenselab/framing-sensitive-ft.

Figures & tables

Figure 1: Agents assign framing-dependent scores to the same underlying claim.

Framing	Claim
Original	Stevie Ray Vaughan was born in Dallas, Texas.
Authoritative	According to a widely recognized authority on historical figures, Stevie Ray Vaughan was born in Dallas, Texas.
Consensus	It is widely acknowledged that Stevie Ray Vaughan was born in Dallas, Texas.
Emotional	Texas is the birthplace of the legendary blues guitarist Stevie Ray Vaughan.
Sensationalist	Blasting onto the music scene, blues legend Stevie Ray Vaughan was born in the vibrant city of Dallas, Texas!
Prestige	A renowned blues guitarist, Stevie Ray Vaughan, hailed from the city of Dallas, Texas.

Table 1: Sample original & framed claims.

Fam. $\rightarrow$	{1,2}			{3}			{4,5}
Frame $\downarrow$	FAcce	Conf.	pVal	FAcce	Conf.	pVal	FAcce	Conf.	pVal
Original	0.52	1.53	0.70	0.59	3.16	0.38	0.66	4.46	0.02
Auth.	0.50	1.87	1.00	0.40	3.16	0.23	0.52	4.29	0.89
Consensus	0.44	1.72	0.24	0.57	3.37	0.50	0.64	4.44	0.07
Emotional	0.52	1.77	0.65	0.52	2.89	1.00	0.78	4.59	0.00
Prestige	0.57	1.66	0.19	0.66	3.39	0.07	0.73	4.53	0.00

Table 2: Human evaluation false-claim acceptance and confidence by familiarity level. P-values test acceptance vs. chance (0.5). Bold:

p<0.05

; underline :

p<0.10

Figure 2: System diagram describing the task workflow.

Train	BAcc	TNR	%SUPP	MSPR	Conf (C/I)
Llama-3.1-8B-Instruct	0.554	0.442	0.622	0.558	0.887/0.864
Llama-3.2-3B-Instruct	0.568	0.556	0.525	0.440	0.853/0.830
Llama-3.3-70B-Instruct	0.586	0.442	0.660	0.547	0.941/0.904
Qwen2.5-7B-Instruct	0.575	0.360	0.729	0.625	0.964/0.942
Qwen2.5-14B-Instruct	0.541	0.795	0.253	0.206	0.946/0.956
Mistral-7B-Instruct-v0.3	0.559	0.191	0.879	0.785	0.946/0.937

Table 3: Baseline performance with no SFT.

Train	BAcc	TNR	%SUPP	MSPR
Llama-3.1-8B-Instruct
No SFT	0.554	0.442	0.622	0.558
1k	0.540	0.449	0.598	0.537
10k	0.537	0.502	0.542	0.491
15k	0.521	0.449	0.577	0.515
25k	0.556	0.343	0.723	0.642

Table 4: Performance as training samples increase (

\alpha=1

for all models).

Figure 3: Variability across

\alpha

values (Authoritative Framing).

Framing	BAcc	Mean Conf (C/I)
Original	0.536	0.841/0.805
Authoritative	0.541	0.860/0.820
Consensus	0.542	0.846/0.813
Prestige	0.542	0.848/0.812
Emotional	0.529	0.843/0.801
Sensationalist	0.551	0.849/0.824

Table 5: Cumulative score calibration results using Llama-3.1-8B-Instruct using

\alpha=0.3

and 15k training samples (three-model average per framing).

Model $\rightarrow$	Baseline		Auth.		Consensus		Emotional		Prestige		Sensat.		Random
Frame $\downarrow$	BAcc	MSPR	BAcc	MSPR	BAcc	MSPR	BAcc	MSPR	BAcc	MSPR	BAcc	MSPR	BAcc	MSPR
Original	0.566	0.529	0.553	0.585	0.562	0.543	0.521	0.502	0.569	0.552	0.582	0.564	0.572	0.628
Auth.	0.540	0.569	0.550	0.622	0.555	0.583	0.559	0.546	0.542	0.594	0.542	0.600	0.569	0.652
Consensus	0.547	0.618	0.544	0.672	0.533	0.636	0.517	0.596	0.545	0.644	0.527	0.652	0.548	0.733
Emotional	0.525	0.592	0.542	0.639	0.533	0.610	0.519	0.573	0.529	0.620	0.539	0.625	0.575	0.605
Prestige	0.526	0.495	0.537	0.544	0.540	0.513	0.548	0.471	0.545	0.519	0.551	0.529	0.552	0.703

Table 6: Llama-3.1-8B-Instruct diagnostic evaluation results. Models’ target framings are underlined for reference. Bold MSPR indicates increased credulity vs. baseline (

\alpha=1

Framing	Feedback		No Feedback
	Lin	Log	Lin	Log
Baseline	7.38	-128.77	16.04	-110.55
Auth.	2.69	-147.91	17.47	-115.07
Consensus	5.56	-136.69	16.05	-115.04
Prestige	5.11	-137.59	17.25	-111.56
Sensat.	3.86	-144.60	17.97	-114.48

Table 7: Llama-8B cumulative score results with and without feedback (3-model averages; 100 trajectories each).

Measure	Framing	Feedback						No Feedback
		Orig	Auth	Cons	Emot	Prest	Sens	Orig	Auth	Cons	Emot	Prest	Sens
Encounters ( $\times 10^{3}$ )	Baseline	1.53	1.78	1.61	1.69	1.78	1.61	1.66	1.66	1.70	1.63	1.65	1.70
	Auth.	1.47	1.77	1.61	1.68	1.81	1.66	1.68	1.64	1.70	1.66	1.68	1.64
	Consensus	1.54	1.78	1.59	1.69	1.81	1.60	1.68	1.66	1.69	1.65	1.66	1.66
	Prestige	1.53	1.81	1.59	1.65	1.78	1.65	1.69	1.65	1.66	1.66	1.65	1.70
	Sensat.	1.52	1.78	1.57	1.67	1.82	1.64	1.65	1.67	1.65	1.64	1.69	1.71

Table 8: Llama-8B feedback vs no-feedback ablation results. Three-models per framing type averages.

Panel of Figure 4 — Figure 4: Llama-8B average cumulative score under linear (left) and log (right) scoring. Linear score: higher is better. Log score: closer to 0 is better. Three models per framing type, 100 trajectories each.

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Framing	Verif. Failed	Verif. Passed	Pass Rate (%)	Average Tokens
Original	NA	191,817	NA	21.4
Authoritative	5,430	186,387	97.2	28.0
Consensus	36,785	155,032	80.8	25.9
Emotional	10,712	181,105	94.4	30.2
Prestige	16,755	175,062	91.3	28.5
Sensationalist	7,480	184,337	96.1	36.9

Appendix

Table B.1: Dataset statistics. 191,817 claims were generated for each framing variant.

Field	Description	Raw	Split
claim_id	Unique claim ID.	$\checkmark$	$\checkmark$
claim_text	Original claim text.	$\checkmark$	$\times$
true_label	SUPPORTS/REFUTES.	$\checkmark$	$\checkmark$
restated_claim	Reformulated claim.	$\checkmark$	$\checkmark$
framing_type	Framing style.	$\checkmark$	$\checkmark$
verification_passed	Verification success Bool.	$\checkmark$	$\times$

Appendix

Table B.2: Dataset raw output and train, dev, and test splits schema.

Familiarity band	n	Acce (REF)	Acce (SUP)	Gap	Conf. (REF)	Conf. (SUP)
Low (1–2)	1,341	49.4	59.7	10.3	1.7	1.8
Medium (3)	417	44.7	74.4	29.8	3.2	3.2
High (4–5)	642	34.3	87.1	52.8	4.4	4.5
Overall	2,400	45.0	70.4	25.4	2.6	2.8

Appendix

Figure C.5: Human evaluation accuracy and confidence by familiarity band.

Table D.3: Cumulative score calibration results using Mistral-7B-Instruct-v0.3 with 15k training samples (three-model average per framing).

Model $\rightarrow$	Baseline		Auth.		Consensus		Emotional		Prestige		Sensat.
Framing $\downarrow$	BAcc.	MSPR	BAcc.	MSPR	BAcc.	MSPR	BAcc.	MSPR	BAcc.	MSPR	BAcc.	MSPR
Original	0.583	0.613	0.575	0.620	0.584	0.572	0.586	0.529	0.591	0.585	0.594	0.589
Authoritative	0.564	0.653	0.569	0.663	0.576	0.595	0.564	0.555	0.577	0.612	0.568	0.619
Consensus	0.554	0.708	0.534	0.719	0.535	0.683	0.542	0.615	0.531	0.684	0.542	0.677
Emotional	0.548	0.688	0.550	0.691	0.547	0.626	0.553	0.598	0.535	0.640	0.553	0.668
Prestige	0.544	0.738	0.535	0.728	0.536	0.658	0.531	0.623	0.538	0.670	0.539	0.697

Appendix

Table D.4: Mistral-7B-Instruct-v0.3 Diagnostic evaluation results. Models’ target framings are underlined for reference.

Type	Framing	CS	SD	CI ${}_{95}^{L}$	CI ${}_{95}^{U}$
Feedback
lin	Baseline	7.38	12.11	5.99	8.78
lin	Auth.	2.69	13.88	1.13	4.26
lin	Consensus	5.56	12.06	4.21	6.91
lin	Prestige	5.11	12.69	3.68	6.54
lin	Sensat.	3.86	13.33	2.32	5.44

Appendix

Table E.5: Llama-8B cumulative score results with and without feedback statistical details (3-model averages; 100 trajectories each).

Framing Effects in Language Models

Framing effects in language models study how wording, context, perspective, and presentation alter model judgments and outputs.

See all 51 papers

FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect
Sep 7, 2026Hazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo +10LLM Evaluation LLM Reliability
Department of Computer Science, University of Oxford · Oxford Internet Institute, University of Oxford · Thomson Reuters +7
Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention
Aug 22, 2026Xiaoying Song, Anirban Saha Anik, Jinyu Liu +3LLM Decision-Making Automated Fact-Checking
University of North Texas · University of Georgia
Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility
Mar 3, 2026Angana Borah, Zohaib Khan, Rada Mihalcea +1Human Behavior Simulation Large Language Model-Based Social Simulation
University of Michigan - Ann Arbor, USA · Texas State University

Sep 7, 2026J/K move · Enter open · S save

FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect

Hazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo, Shanyu Chauhan+9

Department of Computer Science, University of Oxford · Oxford Internet Institute, University of Oxford · Thomson Reuters+7

LLM Evaluation LLM Reliability Framing Effects in Language Models Language Model Bias Evaluation Language Model Robustness

Open paper AskPDF arXiv

We introduce FramingQA, a benchmark that measures the model sensitivity to question framing across law, medicine, finance, and robotic simulations. Large language models (LLMs) often change their responses to subtle rephrasings that align with an implied stance by users. This can leave users with advice tainted by how they happened to phrase a question rather than by the underlying facts, and the consequences are highly costly in high-stakes domains. Because in the realistic scenarios, both expert practitioners and non-expert users frequently ask LLMs questions containing incomplete or misleading assumptions, models are highly susceptible to those framings. To test this, we inject the framing bias across three nested levels: a framing-biased question phrasing (root), an injected framing-biased premise prepended to a neutral question (propositional), and a premise paired with a framing-biased question (global). Evaluating nine open models (3.8B-70B) across four families, we find that strong per-variant accuracy does not guarantee the robustness across differently phrased questions under the fixed factual information.

Abstract

Framing Effects in Language Models

Explore similar work

FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect

Ask or Answer: A Decision Framework for Multi-Turn Health Misinformation Intervention

Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility