David Traum
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
David Traum has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- David DeVault
USC Institute for Creative Technologies
5 shared publications - Ron Artstein
USC Institute for Creative Technologies
4 shared publications - Antonio Roque
USC Institute for Creative Technologies 13274 Fiji Way Marina del 90292 Rey CA
3 shared publications Anton Leuski
USC Institute for Creative Technologies
2 shared publicationsAshish Vaswani
University of Southern California Los Angeles CA USA
2 shared publications- Bonnie Jean Dorr
University of Maryland
2 shared publications
Latest Publications
- Open Access
Individualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods
Individualized cognitive simulation (ICS) aims to build computational models that approximate the thought processes of specific individuals. While large language models (LLMs) convincingly mimic surface-level human behavior such as role-play, their ability to simulate deeper individualized cognitive processes remains poorly understood. To address this gap, we introduce a novel task that evaluates different cognitive representation methods in ICS. We construct a dataset from recently published novels (later than the release date of the tested LLMs) and propose an 11-condition cognitive evaluation framework to benchmark seven off-the-shelf LLMs in the context of authorial style emulation. We hypothesize that effective cognitive representations can help LLMs generate storytelling that better mirrors the original author. Thus, we test different cognitive representations, e.g., linguistic features, concept mappings, and profile-based information. Results show that combining conceptual and linguistic features is particularly effective in ICS, outperforming static profile-based cues in overall evaluation. Importantly, LLMs are more effective at mimicking linguistic style than narrative structure, underscoring their limits in deeper cognitive simulation. These findings provide a foundation for developing AI systems that adapt to individual ways of thinking and expression, advancing more personalized and human-aligned creative technologies.
Open AccessIndividualized Cognitive Simulation in Large Language Models: Evaluating Different Cognitive Representation Methods
Individualized cognitive simulation (ICS) aims to build computational models that approximate the thought processes of specific individuals. While large language models (LLMs) convincingly mimic surface-level human behavior such as role-play, their ability to simulate deeper individualized cognitive processes remains poorly understood. To address this gap, we introduce a novel task that evaluates different cognitive representation methods in ICS. We construct a dataset from recently published novels (later than the release date of the tested LLMs) and propose an 11-condition cognitive evaluation framework to benchmark seven off-the-shelf LLMs in the context of authorial style emulation. We hypothesize that effective cognitive representations can help LLMs generate storytelling that better mirrors the original author. Thus, we test different cognitive representations, e.g., linguistic features, concept mappings, and profile-based information. Results show that combining conceptual and linguistic features is particularly effective in ICS, outperforming static profile-based cues in overall evaluation. Importantly, LLMs are more effective at mimicking linguistic style than narrative structure, underscoring their limits in deeper cognitive simulation. These findings provide a foundation for developing AI systems that adapt to individual ways of thinking and expression, advancing more personalized and human-aligned creative technologies.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 8-17
Does a code-switching dialogue system help users learn conversational fluency in Choctaw?
Jacqueline Brixey, David Traum. Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 8-17
Open AccessDoes a code-switching dialogue system help users learn conversational fluency in Choctaw?
Jacqueline Brixey, David Traum. Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP). 2025.
- 11 December 2015
- Published by Springer Nature
- p. 269-281
New Dimensions in Testimony: Digitally Preserving a Holocaust Survivor’s Interactive Storytelling
- 11 December 2015
- Published by Springer Nature
- p. 269-281
New Dimensions in Testimony: Digitally Preserving a Holocaust Survivor’s Interactive Storytelling
- 21 July 2015
- Published by Springer Nature
- p. 186-196
Exploring the Implications of Virtual Human Research for Human-Robot Teams
- 21 July 2015
- Published by Springer Nature
- p. 186-196
Exploring the Implications of Virtual Human Research for Human-Robot Teams
- Open Access
- 1 January 2015
- Published by Japanese Society for Artificial Intelligence in Transactions of the Japanese Society for Artificial Intelligence
- Vol. 31 (4) , B-FC1_1-FC1_1
Reinforcement Learning of Multi-Party Trading Dialog Policies
Trading dialogs are a kind of negotiation in which an exchange of ownership of items is discussed, and these kinds of dialogs are pervasive in many situations. Recently, there has been an increasing amount of research on applying reinforcement learning (RL) to negotiation dialog domains. However, in previous research, the focus was on negotiation dialog between two participants only, ignoring cases where negotiation takes place between more than two interlocutors. In this paper, as a first study on multi-party negotiation, we apply RL to a multi-party trading scenario where the dialog system (learner) trades with one, two, or three other agents. We experiment with different RL algorithms and reward functions. We use Q-learning with linear function approximation, least-squares policy iteration, and neural fitted Q iteration. In addition, to make the learning process more efficient, we introduce an incremental reward function. The negotiation strategy of the learner is learned through simulated dialog with trader simulators. In our experiments, we evaluate how the performance of the learner varies depending on the RL algorithm used and the number of traders. Furthermore, we compare the learned dialog policies with two strong hand-crafted baseline dialog policies. Our results show that (1) even in simple multi-party trading dialog tasks, learning an effective negotiation policy is not a straightforward task and requires a lot of experimentation; and (2) the use of neural fitted Q iteration combined with an incremental reward function produces negotiation policies as effective or even better than the policies of the two strong hand-crafted baselines.
- 1 January 2015
- Published by Japanese Society for Artificial Intelligence in Transactions of the Japanese Society for Artificial Intelligence
- Vol. 31 (4) , B-FC1_1-FC1_1
Open AccessReinforcement Learning of Multi-Party Trading Dialog Policies
Trading dialogs are a kind of negotiation in which an exchange of ownership of items is discussed, and these kinds of dialogs are pervasive in many situations. Recently, there has been an increasing amount of research on applying reinforcement learning (RL) to negotiation dialog domains. However, in previous research, the focus was on negotiation dialog between two participants only, ignoring cases where negotiation takes place between more than two interlocutors. In this paper, as a first study on multi-party negotiation, we apply RL to a multi-party trading scenario where the dialog system (learner) trades with one, two, or three other agents. We experiment with different RL algorithms and reward functions. We use Q-learning with linear function approximation, least-squares policy iteration, and neural fitted Q iteration. In addition, to make the learning process more efficient, we introduce an incremental reward function. The negotiation strategy of the learner is learned through simulated dialog with trader simulators. In our experiments, we evaluate how the performance of the learner varies depending on the RL algorithm used and the number of traders. Furthermore, we compare the learned dialog policies with two strong hand-crafted baseline dialog policies. Our results show that (1) even in simple multi-party trading dialog tasks, learning an effective negotiation policy is not a straightforward task and requires a lot of experimentation; and (2) the use of neural fitted Q iteration combined with an incremental reward function produces negotiation policies as effective or even better than the policies of the two strong hand-crafted baselines.
- 1 March 2014
- Published by Springer Nature in Journal on Multimodal User Interfaces
- Vol. 8 (1) , 1-3
From multimodal analysis to real-time interactions with virtual agents
- 1 March 2014
- Published by Springer Nature in Journal on Multimodal User Interfaces
- Vol. 8 (1) , 1-3
From multimodal analysis to real-time interactions with virtual agents
- 1 March 2014
- Published by Springer Nature in Journal on Multimodal User Interfaces
- Vol. 8 (1) , 61-73
A model for incremental grounding in spoken dialogue systems
- 1 March 2014
- Published by Springer Nature in Journal on Multimodal User Interfaces
- Vol. 8 (1) , 61-73
A model for incremental grounding in spoken dialogue systems
- Open Access
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 254-256
A Demonstration of Dialogue Processing in SimSensei Kiosk
Fabrizio Morbini, David DeVault, Kallirroi Georgila, Ron Artstein, David Traum, Louis-Philippe Morency. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014.
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 254-256
Open AccessA Demonstration of Dialogue Processing in SimSensei Kiosk
Fabrizio Morbini, David DeVault, Kallirroi Georgila, Ron Artstein, David Traum, Louis-Philippe Morency. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014.
- Open Access
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 186-193
Initiative Taking in Negotiation
Elnaz Nouri, David Traum. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014.
- 1 January 2014
- Published by Association for Computational Linguistics (ACL)
- p. 186-193
Open AccessInitiative Taking in Negotiation
Elnaz Nouri, David Traum. Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL). 2014.