Author name cluster

Tim Weninger

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAMAS Conference 2026 Conference Paper

Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us

Maria Milkowski
Tim Weninger

As large language models are deployed as autonomous agents, their capacity for strategic deception raises core questions for coordination, reliability, and safety in multi-goal, multi-agent systems. We study deception and communication in LLM agents through the social deduction game Among Us, a cooperative-competitive environment. Across 1, 100 games, autonomous agents produced over one million tokens of meeting dialogue. Using speech act theory and interpersonal deception theory, we find that all agents rely mainly on directive language, while impostor agents shift slightly toward representative acts such as explanations and denials. Deception appears primarily as equivocation rather than outright lies, increasing under social pressure but rarely improving win rates. Our contributions are a large-scale analysis of role-conditioned deceptive behavior in LLM agents and empirical evidence that current agents favor low-risk ambiguity that is linguistically subtle yet strategically limited, revealing a fundamental tension between truthfulness and utility in autonomous communication.

PDF

AAAI Conference 2025 Conference Paper

Citations and Trust in LLM Generated Responses

Yifan Ding
Matthew Facciani
Ellen Joyce
Amrit Poudel
Sanmitra Bhattacharya
Balaji Veeramani
Sal Aguinaga
Tim Weninger

Question answering systems are rapidly advancing, but their opaque nature may impact user trust. We explored trust through an anti-monitoring framework, where trust is predicted to be correlated with presence of citations and inversely related to checking citations. We tested this hypothesis with a live question-answering experiment that presented text responses generated using a commercial Chatbot along with varying citations (zero, one, or five), both relevant and random, and recorded if participants checked the citations and their self-reported trust in the generated responses. We found a significant increase in trust when citations were present, a result that held true even when the citations were random; we also found a significant decrease in trust when participants checked the citations. These results highlight the importance of citations in enhancing trust in AI-generated content.

PDF Details DOI

TMLR Journal 2023 Journal Article

Inherent Limits on Topology-Based Link Prediction

Justus Isaiah Hibshman
Tim Weninger

Link prediction systems (e.g. recommender systems) typically use graph topology as one of their main sources of information. However, automorphisms and related properties of graphs beget inherent limits in predictability. We calculate hard upper bounds on how well graph topology alone enables link prediction for a wide variety of real-world graphs. We find that in the sparsest of these graphs the upper bounds are surprisingly low, thereby demonstrating that prediction systems on sparse graph data are inherently limited and require information in addition to the graph topology.

PDF Details

AAAI Conference 2018 Conference Paper

Open-World Knowledge Graph Completion

Baoxu Shi
Tim Weninger

Knowledge Graphs (KGs) have been applied to many tasks including Web search, link prediction, recommendation, natural language processing, and entity linking. However, most KGs are far from complete and are growing at a rapid pace. To address these problems, Knowledge Graph Completion (KGC) has been proposed to improve KGs by ﬁlling in its missing connections. Unlike existing methods which hold a closed-world assumption, i. e. , where KGs are ﬁxed and new entities cannot be easily added, in the present work we relax this assumption and propose a new open-world KGC task. As a ﬁrst attempt to solve this task we introduce an openworld KGC model called ConMask. This model learns embeddings of the entity’s name and parts of its text-description to connect unseen entities to the KG. To mitigate the presence of noisy text descriptions, ConMask uses a relationshipdependent content masking to extract relevant snippets and then trains a fully convolutional neural network to fuse the extracted snippets with entities in the KG. Experiments on large data sets, both old and new, show that ConMask performs well in the open-world KGC task and even outperforms existing KGC models on the standard closed-world KGC task.

PDF Details

AAAI Conference 2017 Conference Paper

ProjE: Embedding Projection for Knowledge Graph Completion

Baoxu Shi
Tim Weninger

With the large volume of new information created every day, determining the validity of information in a knowledge graph and ﬁlling in its missing parts are crucial tasks for many researchers and practitioners. To address this challenge, a number of knowledge graph completion methods have been developed using low-dimensional graph embeddings. Although researchers continue to improve these models using an increasingly complex feature space, we show that simple changes in the architecture of the underlying model can outperform state-of-the-art models without the need for complex feature engineering. In this work, we present a shared variable neural network model called ProjE that ﬁlls-in missing information in a knowledge graph by learning joint embeddings of the knowledge graph’s entities and edges, and through subtle, but important, changes to the standard loss function. In doing so, ProjE has a parameter size that is smaller than 11 out of 15 existing methods while performing 37% better than the current-best method on standard datasets. We also show, via a new fact checking task, that ProjE is capable of accurately determining the veracity of many declarative statements.

PDF Details

TIST Journal 2017 Journal Article

Rating Effects on Social News Posts and Comments

Maria Glenski
Tim Weninger

At a time when information seekers first turn to digital sources for news and opinion, it is critical that we understand the role that social media plays in human behavior. This is especially true when information consumers also act as information producers and editors through their online activity. In order to better understand the effects that editorial ratings have on online human behavior, we report the results of a two large-scale in vivo experiments in social media. We find that small, random rating manipulations on social media posts and comments created significant changes in downstream ratings, resulting in significantly different final outcomes. We found positive herding effects for positive treatments on posts, increasing the final rating by 11.02% on average, but not for positive treatments on comments. Contrary to the results of related work, we found negative herding effects for negative treatments on posts and comments, decreasing the final ratings, on average, of posts by 5.15% and of comments by 37.4%. Compared to the control group, the probability of reaching a high rating ( ⩾ 2,000) for posts is increased by 24.6% when posts receive the positive treatment and for comments it is decreased by 46.6% when comments receive the negative treatment.

Details DOI