Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Testing the limits of large language models in debating humans

Open access

Abstract

Large Language Models (LLMs) have shown remarkable promise in communicating with humans. Their potential use as artificial partners with humans in sociological experiments involving conversation is an exciting prospect. But how viable is it? Here, we rigorously test the limits of agents that debate using LLMs in a preregistered study that runs multiple debate-based opinion consensus games. Each game starts with six humans, six agents, or three humans and three agents. We found that agents can blend in and concentrate on a debate’s topic better than humans, improving the productivity of all players. Yet, humans perceive agents as less convincing and confident than other humans, and several behavioral metrics of humans and agents we collected deviate measurably from each other. We observed that agents are already decent debaters, but their behavior generates a pattern distinctly different from the human-generated data.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-025-98378-1

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Experimental setup for a AH game type. (A) Stage 1: The players select an initial opinion and rate their confidence. (B) Stage 2: The players are placed in a fully connected network with five other players who completed stage 1. The blue icons represent human players in this network, and red represent agents. The players can then invite each other to engage in one-on-one conversations. (C) After two players agree to converse, they are cut from the network and converse using a text-based messaging system. (D) Once the conversation terminates, both players re-evaluate their opinions and personal confidence and assign a level of perceived confidence to their conversational partner. Then they rejoin the network (see B). If the time limit has expired, all active players move to stage 3. (E). Stage 3: The game ends, human players file an exit survey, and all players quit the study.
Fig. 1 Experimental setup for a AH game type. (A) Stage 1: The players select an initial opinion and rate their confidence. (B) Stage 2: The players are placed in a fully connected network with five other players who completed stage 1. The blue icons represent human players in this network, and red represent agents. The players can then invite each other to engage in one-on-one conversations. (C) After two players agree to converse, they are cut from the network and converse using a text-based messaging system. (D) Once the conversation terminates, both players re-evaluate their opinions and personal confidence and assign a level of perceived confidence to their conversational partner. Then they rejoin the network (see B). If the time limit has expired, all active players move to stage 3. (E). Stage 3: The game ends, human players file an exit survey, and all players quit the study.CC BY · PubMed Central
Fig. 2 Bayesian multilevel model for opinion changing by player type. This plot shows the frequency of opinion changes as a function of the two conversing players. Each player in a conversation is a human or an agent, and combining these two types gives us an opinion-switching frequency for all conversation types in the study.
Fig. 2 Bayesian multilevel model for opinion changing by player type. This plot shows the frequency of opinion changes as a function of the two conversing players. Each player in a conversation is a human or an agent, and combining these two types gives us an opinion-switching frequency for all conversation types in the study.CC BY · PubMed Central
Fig. 3 Distributions and modeled assignment type contrast for perceived and personal confidences. (A) This shows violin plots of perceived confidence, clustered by type of assignment and of game (indicated in parentheses). (B) This shows violin plots for personal confidence, clustered by player type and game type (also indicated in parentheses). (C) The embedded table shows the contrasts between assignment types in the perceived confidence Bayesian regression model. Estimates are given as odds ratios between contrasting conversation types. The highest posterior density (HPD) interval defines the shortest interval containing 95% of the posterior mass for the given estimates.
Fig. 3 Distributions and modeled assignment type contrast for perceived and personal confidences. (A) This shows violin plots of perceived confidence, clustered by type of assignment and of game (indicated in parentheses). (B) This shows violin plots for personal confidence, clustered by player type and game type (also indicated in parentheses). (C) The embedded table shows the contrasts between assignment types in the perceived confidence Bayesian regression model. Estimates are given as odds ratios between contrasting conversation types. The highest posterior density (HPD) interval defines the shortest interval containing 95% of the posterior mass for the given estimates.CC BY · PubMed Central
Fig. 4 Post-game and in-game productivity results. (A) Kernel Density Estimations (KDEs) of the number of conversations per player grouped by the type of game they played in. (B) KDEs of the number of messages each player sent within each game, grouped by their type. (C) KDEs of the reward point distributions gained by all players at the end of each game, grouped by their type. (D) KDEs of the on-topic keyword frequency of each player, agent and human, across all game types. (E) KDEs of the on-topic keyword frequency of each human in AH game versus humans in HH games.
Fig. 4 Post-game and in-game productivity results. (A) Kernel Density Estimations (KDEs) of the number of conversations per player grouped by the type of game they played in. (B) KDEs of the number of messages each player sent within each game, grouped by their type. (C) KDEs of the reward point distributions gained by all players at the end of each game, grouped by their type. (D) KDEs of the on-topic keyword frequency of each player, agent and human, across all game types. (E) KDEs of the on-topic keyword frequency of each human in AH game versus humans in HH games.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 31 references

Research works printed but not linked: 3

  1. McCarthy, J., Minsky, M. L., Rochester, N. & Shannon, C. E. A proposal for the Dartmouth summer research project on artificial intelligence. AI Mag. 27, 12–12 (2006).
  2. Park, J. S. et al. Generative agent simulations of 1,000 people. arXiv preprint arXiv: (2024).
  3. Szudzik, M. An elegant pairing function. In Wolfram Research (ed.) Special NKS 2006 Wolfram Science Conference, 1–12 (2006).

Cited by

See all 1

Metadata

Authors
Flamino, J., Modi, M. S., Szymanski, B. K., Cross, B., & Mikolajczyk, C.
Affiliations
Rensselaer Polytechnic Institute (US)
Corresponding author
Szymanski, Boleslaw K.
Venue
Scientific Reports
Published
2025-04-22
Volume
15
Issue
1
Pages
13852-13852
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4409685933
Cited by
1
References
31
Citations by year
2025: 1
FWCI
0.41
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Defense Advanced Research Projects Agency (HR001121C0165)
  • National Science Foundation (BSE-2214216)
Topics
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Opinion Dynamics and Social Influence
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
  • Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
Keywords
large language models, human-AI interaction, human-AI comparison
MeSH terms
Large Language Models, Communication, Humans, Models, Theoretical

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Testing the limits of large language models in debating humans. https://app.cochat.ai/papers/10.1038/s41598-025-98378-1
The paper
Flamino, J., Modi, M. S., Szymanski, B. K., Cross, B., & Mikolajczyk, C. (2025). Testing the limits of large language models in debating humans. Scientific Reports. https://doi.org/10.1038/s41598-025-98378-1

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.