paper-with-me

홈 › Papers

LLMs as mediators: Can they diagnose conflicts accurately?

2024-12-19 · Özgecan Koçak, Phanish Puranam, Afşar Yegin

Prior research indicates that to be able to mediate conflict, observers of disagreements between parties must be able to reliably distinguish the sources of their disagreement as stemming from differences in beliefs about what is true (causality) vs. differences in what they value (morality). In this paper, we test if OpenAI's Large Language Models GPT 3.5 and GPT 4 can perform this task and whether one or other type of disagreement proves particularly challenging for LLM's to diagnose. We replicate study 1 in Ko\c{c}ak et al. (2003), which employes a vignette design, with OpenAI's GPT 3.5 and GPT 4. We find that both LLMs have similar semantic understanding of the distinction between causal and moral codes as humans and can reliably distinguish between them. When asked to diagnose the source of disagreement in a conversation, both LLMs, compared to humans, exhibit a tendency to overestimate the extent of causal disagreement and underestimate the extent of moral disagreement in the moral misalignment condition. This tendency is especially pronounced for GPT 4 when using a proximate scale that relies on concrete language specific to an issue. GPT 3.5 does not perform as well as GPT4 or humans when using either the proximate or the distal scale. The study provides a first test of the potential for using LLMs to mediate conflict by diagnosing the root of disagreements in causal and evaluative codes.

📄 PDF Abstract BibTeX arXiv:2412.14675

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars?

2025-12-02 · Dawei Li, Abdullah Alnaibari, Arslan Bisharat, Manuel Sandoval 외 arxiv

The rapid advancement of large language models (LLMs) has opened new possibilities for AI for good applications. As LLMs increasingly mediate online communication, their potential to foster empathy and constructive dialo…

Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators

2025-07-08 · Sungjib Lim, Woojung Song, Eun-Ju Lee, Yohan Jo arxiv

As psychometric surveys are increasingly used to assess the traits of large language models (LLMs), the need for scalable survey item generation suited for LLMs has also grown. A critical challenge here is ensuring the c…

SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations

2026-06-04 · Taewon Yun, Hyeonseong Park, Jeonghwan Choi, Hayoon Park 외 arxiv

Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context. Existing testbeds rely on a few expert-authored domains, vary…

Machine Learning for Mediation in Armed Conflicts

2021-08-26 · M. Arana-Catania, F. A. Van Lier, Rob Procter

Today's conflicts are becoming increasingly complex, fluid and fragmented, often involving a host of national and international actors with multiple and often divergent interests. This development poses significant chall…

BIG-bench Machine Learning

Polistemics: Evaluating LLMs as Information Mediators in Politics & Elections

2026-07-28 · Baran Peters arxiv

As LLMs increasingly mediate the political information citizens rely on, there is still no standardized way to assess whether they do so responsibly. We introduce Polistemics, a theory-grounded benchmark for evaluating L…