# BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts

arXiv: https://arxiv.org/abs/2512.24885 · HTML: https://mlsanity.com/paper/2512.24885/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments](https://mlsanity.com/paper/1710.03641/) (2017)
- [CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems](https://mlsanity.com/paper/2103.15721/) (2021)
- [Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings](https://mlsanity.com/paper/1704.07130/) (2017)
- [Few-shot Language Coordination by Modeling Theory of Mind](https://mlsanity.com/paper/2107.05697/) (2021)
- [Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games](https://mlsanity.com/paper/2312.00746/) (2023)
- [Dialogue Act Classification with Context-Aware Self-Attention](https://mlsanity.com/paper/1904.02594/) (2019)
- [Speaker Turn Modeling for Dialogue Act Classification](https://mlsanity.com/paper/2109.05056/) (2021)
- [Emergence of Pragmatics from Referential Game between Theory of Mind Agents](https://mlsanity.com/paper/2001.07752/) (2020)
- [Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate](https://mlsanity.com/paper/2408.04472/) (2024)
- [DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning](https://mlsanity.com/paper/2306.09030/) (2023)
- [Infusing Theory of Mind into Socially Intelligent LLM Agents](https://mlsanity.com/paper/2509.22887/) (2025)
- [Game Theory (Open Access textbook with 165 solved exercises)](https://mlsanity.com/paper/1512.06808/) (2015)

## Built on by (most cited first, 2 of 2)

- [Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency](https://mlsanity.com/paper/2601.05905/) (2026)
- [Distilling Bayesian Belief States into Language Models for Auditable Negotiation](https://mlsanity.com/paper/2605.04507/) (2026)

## Abstract (arXiv)

Strategic dialogue requires agents to execute distinct dialogue acts, for which belief estimation is essential. While prior work often estimates beliefs accurately, it lacks a principled mechanism to use those beliefs during generation. We bridge this gap by first formalizing two core acts Adversarial and Alignment, and by operationalizing them via probabilistic constraints on what an agent may generate. We instantiate this idea in BEDA, a framework that consists of the world set, the belief estimator for belief estimation, and the conditional generator that selects acts and realizes utterances consistent with the inferred beliefs. Across three settings, Conditional Keeper Burglar (CKBG, adversarial), Mutual Friends (MF, cooperative), and CaSiNo (negotiation), BEDA consistently outperforms strong baselines: on CKBG it improves success rate by at least 5.0 points across backbones and by 20.6 points with GPT-4.1-nano; on Mutual Friends it achieves an average improvement of 9.3 points; and on CaSiNo it achieves the optimal deal relative to all baselines. These results indicate that casting belief estimation as constraints provides a simple, general mechanism for reliable strategic dialogue.