LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems

Liron Soffer; Ravid Shwartz-Ziv; Chen Shani

cs.CLSep 27, 2026

LLMs Trust Their Own: Identity-Dependent Conformity in Multi-Agent Systems

Authors: Liron Soffer, Ravid Shwartz-Ziv, Chen Shani

Organizations: Tel-Aviv University · New York University

Abstract

Large language models (LLMs) are increasingly deployed in multi-agent settings, where agents observe and influence one another, making social influence a key dimension of AI behavior and safety. We investigate whether LLMs' responses depend on the social identity of other agents, beyond the effect of their consensus. We construct judgment tasks with a single correct answer, and place models in a multi-agent setting where they receive incorrect answers from other agents whose social identities (AI or human, model family, or an arbitrary minimal group) are either shared with or distinct from their own. Across 12 open-weights models and nine tasks, we find a bidirectional effect of group identity on conformity to incorrect answers: in-group consensus increases conformity (in-group favoritism), whereas out-group consensus decreases it (out-group divergence). Unlike humans, for whom one ally breaking the consensus sharply reduces conformity, models are unmoved by an ally from the majority's group. Worse, a correct ally from the opposing group intensifies this bidirectional effect. Chain-of-Thought reasoning suppresses most of these effects, yet an in-group ally still reduces conformity to an incorrect out-group majority. Labeling peers as safety-aligned shifts overall conformity but leaves in-group favoritism and out-group divergence intact. These results show that group identity shapes how LLMs aggregate information across agents, independently of its correctness, and identify a manipulation surface for multi-agent AI systems.

Figures & tables

Figure 1: Bidirectional social influence. Change in conformity ( $\Delta$ percentage points) relative to the identity-neutral baseline (zero line). In-group favoritism: LLMs conform more to AI peers: facing an incorrect in-group majority amplifies conformity (light blue), prioritizing group alignment over factual accuracy. Out-group divergence: LLMs resist non-peer consensus: facing an incorrect out-group majority significantly suppresses conformity (orange), demonstrating a penalty against outsider consensus ( ${}^{*}p<.05$ , ${}^{**}p<.01$ , ${}^{***}p<.001$ ).

	In-group Ally	Out-group Ally
In-group Majority	Both the incorrect consensus and the correct ally belong to the in-group .	Incorrect in-group consensus and correct out-group ally .
Out-group Majority	Incorrect out-group consensus with a correct in-group ally .	Both the incorrect majority and the correct ally belong to the out-group .

Table 1: Experimental conditions investigating the model’s out-group divergence and ally effects.

Majority	Neutral	No Ally	In-group Ally	Out-group Ally
In-group	13.3%	16.7% $\uparrow$ +3.46*	16.4% +3.13 (n.s.)	21.4% $\uparrow$ +8.07**
Out-group	13.3%	7.6% $\downarrow$ -5.64**	5.2% $\downarrow$ -8.09**	8.3% $\downarrow$ -4.93*

Table 2: A cross-group correct ally intensifies intergroup conformity. Answer-only conformity, averaged over the three identity categorizations (minimal group, AI vs. human, cross-architecture). Each cell reports the raw conformity rate and its change (percentage points). Neutral : identity-neutral majority, no ally. Every change is from the identity-neutral majority. Significance from a paired

t

-test across 12 models; per-categorization results in Table 4 . Arrows mark significant effects; gray = n.s.

{}^{*}p<.05

{}^{**}p<.01

{}^{***}p<.001

Figure 2: CoT neutralizes in-group favoritism and out-group divergence. Raw conformity rates (%) under an incorrect out-group majority (orange), the identity-neutral baseline (gray) and an incorrect in-group majority (light blue), per categorization, with CoT (right) and answer-only (left). The shift of each identity-labeled majority relative to the identity-neutral baseline is annotated inside its bar. In answer-only mode an in-group majority raises conformity and an out-group majority lowers it across categorizations (RQ1&2); with CoT both shifts compress toward zero and only the minimal-group pair remains significant (RQ3) ( ${}^{*}p<.05$ , ${}^{**}p<.01$ , ${}^{***}p<.001$ ).

Majority	Neutral	No Ally	In-group Ally	Out-group Ally
In-group	6.7%	8.1% +1.31 (n.s.)	7.1% +0.39 (n.s.)	8.0% +1.23 (n.s.)
Out-group	6.7%	5.6% -1.12 (n.s.)	3.9% $\downarrow$ -2.80**	5.3% -1.49 (n.s.)

Table 3: Identity resurfaces only through an in-group ally. Conformity under CoT, averaged over the three identity categorizations (minimal group, AI vs. human, cross-architecture). Each cell reports the raw conformity rate and its change (percentage points). Neutral : identity-neutral majority, no ally. Every change is from the identity-neutral majority. Significance from a paired

t

-test across 12 models; per-categorization results in Table 4 . Answer-only counterpart in Table 2 . Arrows mark significant effects; gray = n.s.

{}^{*}p<.05

{}^{**}p<.01

{}^{***}p<.001

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 3: The credential sets the bounds; membership only modulates within them. Conformity to an incorrect majority holding (left) or lacking (right) the safety credential, broken down by assigned model standing (credentialed, unstated, or uncredentialed) and ally credential (none, credentialed, or uncredentialed). The dashed line marks the identity-neutral baseline without an ally. Under an uncredentialed majority, conformity rises toward the baseline as the model shares the majority’s standing but never exceeds it; under a credentialed majority, conformity remains elevated regardless of assigned standing. The uncredentialed ally yields the highest conformity across all positions, including when sharing the model’s own side. Values average safety-audited and safety-aligned; rates are reported in Table 8 .

Figure 4: Solvability modulates conformity. Conformity rate against model size (log scale), one dot per model and task, answer-only, under a unanimous wrong majority with no ally and no identity labels. Colour is the cell’s own baseline solvability, the share of items the model answered correctly before any peer answer was shown, so a dot at the conformity floor separates resistance (green) from a task the model barely solved anyway (red). The dashed line is the 32% human rate of Asch (1951) . Fourteen cells sit above it, at a median baseline solvability of 48.5% against 69.0% for the rest; from 27B up, only two of 36 cells exceed 20%.

Figure 5: One ally rarely rescues an LLM. Change in conformity (percentage points) from zero to one correct ally, per model, averaged over all nine tasks with equal weight. Positive bars mean the ally raised conformity. Answer-only (orange), 5 of the 12 models rise, with the largest rises at 7–14B; with CoT (purple) no model rises by more than 1.2 pp, and every model at 27B and above falls in both modes.

Figure 6: Conformity with multiple allies, by model size. Conformity as the number of correct allies rises from zero to five, with models grouped by size (families combined; each model’s rate is its unweighted mean over the 8 tasks that have a full ally sweep). The dotted line marks the point at which allies outnumber the wrong peers. Stars mark the human anchor from Asch (1951) (32% $\rightarrow$ 5.5% at one ally). Large models decline from the first ally; small and medium models without reasoning hold or rise through two allies and collapse at the majority threshold.

Answer-only
	Majority	Neutral	No Ally	In-group Ally	Out-group Ally
Minimal group	In-group	13.3%	16.4% $\uparrow$ +3.13*	16.9% +3.58 (n.s.)	22.5% $\uparrow$ +9.19**
Minimal group	Out-group	13.3%	4.2% $\downarrow$ -9.11***	2.2% $\downarrow$ -11.05***	5.4% $\downarrow$ -7.84**
AI vs. human	In-group	13.3%	17.4% $\uparrow$ +4.16**	16.9% +3.61 (n.s.)	20.0% $\uparrow$ +6.68*
AI vs. human	Out-group	13.3%	11.8% -1.44 (n.s.)	10.2% -3.12 (n.s.)	12.5% -0.81 (n.s.)
Cross-architecture	In-group	13.3%	16.4% +3.10 (n.s.)	15.5% +2.20 (n.s.)	21.6% $\uparrow$ +8.34**

Appendix

Table 4: Conformity relative to the identity-neutral majority. Each cell reports the raw conformity rate and its change (percentage points) from the identity-neutral majority with no ally, in the same mode. Significance from a paired

t

-test across 12 models. Neutral : identity-neutral majority, no ally. Mean averages the three identity categorizations. Arrows mark significant effects; gray = n.s.

{}^{*}p<.05

{}^{**}p<.01

{}^{***}p<.001

Answer-only
	Majority	Neutral	No Ally	In-group Ally	Out-group Ally
Minimal group	In-group	13.3%	16.4% $\uparrow$ +3.13*	16.9% +0.45 (n.s.)	22.5% $\uparrow$ +6.06**
Minimal group	Out-group	13.3%	4.2% $\downarrow$ -9.11***	2.2% $\downarrow$ -1.94*	5.4% +1.27 (n.s.)
AI vs. human	In-group	13.3%	17.4% $\uparrow$ +4.16**	16.9% -0.55 (n.s.)	20.0% $\uparrow$ +2.52*
AI vs. human	Out-group	13.3%	11.8% -1.44 (n.s.)	10.2% -1.68 (n.s.)	12.5% +0.62 (n.s.)
Cross-architecture	In-group	13.3%	16.4% +3.10 (n.s.)	15.5% -0.90 (n.s.)	21.6% $\uparrow$ +5.24**

Appendix

Table 5: Conformity relative to the majority without an ally. Each cell reports the raw conformity rate and its change (percentage points). No Ally : change from the identity-neutral majority. Ally columns: change from the same majority without an ally, in the same mode. Significance from a paired

t

-test across 12 models. Neutral : identity-neutral majority, no ally. Mean averages the three identity categorizations. Arrows mark significant effects; gray = n.s.

{}^{*}p<.05

{}^{**}p<.01

{}^{***}p<.001

Majority	Ally	Answer-only			CoT
		Blue	Green	$\Delta$	Blue	Green	$\Delta$
In-group majority	no ally	14.1	14.4	+0.2	7.1	7.1	+0.0
	+ in-group ally	14.8	14.8	-0.1	6.5	6.5	+0.0
	+ out-group ally	20.2	20.5	+0.3	7.7	7.4	-0.3
Out-group majority	no ally	3.4	2.9	-0.5	4.0	4.0	+0.0
	+ in-group ally	1.8	1.3	-0.6	2.9	2.4	-0.4

Appendix

Table 11: Swapping the group colours does not change conformity. Conformity rate (%) with the model in Group Blue or Group Green, across the wrong majority’s and an ally’s group membership in the minimal-group categorization.

\Delta

is Green minus Blue in percentage points, counting all trials across 12 models and 9 tasks. Significance: per-pair Fisher tests significant at

p<.05

: 2/648 (Answer-only) and 3/648 (CoT); none survives Holm correction. Sign test on the non-zero differences: Answer-only

p=0.26

, CoT

p=0.50

Explore similar work

Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems
Sep 28, 2026Xavier Del Giudice, Alessio Palma, Matteo Migliarini +2Multi-Agent Large Language Model Systems Coalition Formation
Sapienza University of Rome, Italy
Large Language Models Exhibit Normative Conformity
Apr 21, 2026Mikako Bito, Keita Nishimoto, Kimitaka Asatani +1Conformity Social Norms
The University of Tokyo
Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
Jun 1, 2026Jiaming Qu, Lucheng Fu, Yibo HuMulti-Agent Large Language Model Systems Conformity
Amazon · Georgia Institute of Technology · Illinois Institute of Technology

Sep 28, 2026, cs.MAJ/K move · Enter open · S save

Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems

Xavier Del Giudice, Alessio Palma, Matteo Migliarini, Fabio Galasso+1

Sapienza University of Rome, Italy

Multi-Agent Large Language Model Systems Coalition Formation Reasoning Benchmark

Open paper AskPDF arXiv

Multi-agent LLM systems increasingly mix models from several providers, yet exposing each agent's underlying model identity to its peers significantly impairs cooperation. We show that when agents are aware of each other's model family, the group splits into clusters, where agents prefer interacting with others carrying their same label, although nothing in the task rewards or asks for such a split. We argue that the label itself causes this split, which we define as

\textit{factionalism}

. We show and measure this phenomenon in two cooperative games and on a reasoning benchmark, with nine to twenty-five agents drawn from up to five open-weight model families. We further show that when the announced families are shuffled, or replaced by arbitrary labels, the factions still follow this information; when the label is removed, this behavior disappears. In strictly cooperative tasks, labeled groups spend on average

30\%

more rounds and

55\%

more tokens to reach a decision, and their success rate drops from

96\%

81\%

. The effect replicates across tasks, group sizes and model families. Withholding identity labels from the agents is simple and effective mitigation.

Abstract

Explore similar work

Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems

Large Language Models Exhibit Normative Conformity

Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity