Challenge: Non-collaborative dialogue involves two participants with conflicting interests engaging in multiround dialogue to achieve their own goals.
Approach: They propose a Game-based Adversarial self-play InterActive training paradigm which constructs an adversarial two-player (a persuader and a resister) zero-sum game and guides the game to approximate Nash Equilibrium (NE) via reinforcement learning.
Outcome: The proposed model achieves state-of-the-art performance on three datasets.

Similar Papers

Evaluating and Enhancing the Robustness of Dialogue Systems: A Case Study on a Negotiation Agent (N19-1)

Copied to clipboard

Challenge: Recent research has demonstrated that goal-oriented dialogue agents can achieve striking performance when interacting with human users.
Approach: They develop algorithms to evaluate the robustness of a goal-oriented dialogue agent by carefully designed attacks using adversarial agents.
Outcome: The proposed attacks reduce the advantage of rewards between the attacker and the trained agent from 2.68 to -5.76 on a scale from -10 to 10 for randomized goals.
Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation (2024.emnlp-main)

Copied to clipboard

Challenge: Non-collaborative dialogue agents are expected to engage in strategic conversations with diverse users, and this poses two main challenges for existing dialogue agents: 1) the inability to integrate user-specific characteristics into the strategic planning; 2) the difficulty of training strategic planners that can be generalized to diverse users.
Approach: They propose to integrate a user-aware strategic planning module and a population-based training paradigm into a non-collaborative dialogue agent for securing a mutual agreement that leans favorably towards the system's objectives.
Outcome: The proposed model can be used to achieve a mutual agreement that leans favorably towards the system's objectives.
ASTRO: Automatic Strategy Optimization For Non-Cooperative Dialogues (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for optimizing dialogues require substantial human effort for strategy optimization.
Approach: They propose a fully automated solution that leverages large language models’ self-envolving capabilities to optimize dialogue strategies.
Outcome: The proposed solution significantly improves on baseline models across non-cooperative dialogue tasks, highlighting the potential for autonomously developing such agents without human intervention.
Teaching Models to Balance Resisting and Accepting Persuasion (2025.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are susceptible to persuasion, which can pose risks when faced with an adversarial interlocutor.
Approach: They propose a method to balance positive and negative persuasion by using recursive dialogue trees to train models to accept persulasion.
Outcome: The proposed model-based training improves resistance to misinformation and resilience to being challenged while also resulting in the best overall performance on multi-agent debates across two domains.
Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Copied to clipboard

Challenge: Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach: They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome: The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.
ResPer: Computationally Modelling Resisting Strategies in Persuasive Conversations (2021.eacl-main)

Copied to clipboard

Challenge: Existing research has failed to account for resisting strategies employed to foil persuasion attempts.
Approach: They propose a framework for identifying resisting strategies in persuasive conversations . they instantiate a dataset comprising persuasion and negotiation conversations based on a hierarchical sequence-labelling neural architecture .
Outcome: The proposed framework is based on two persuasive conversation datasets and leverages a hierarchical sequence-labelling neural architecture to infer resisting strategies automatically.
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing defenses, including post-training alignment and prompt engineering, struggle with adaptability to out-of-distribution (OOD) attacks.
Approach: They propose an adversarial game-based defense method that dynamically adjusts LLMs’ internal representations to achieve a balanced trade-off between helpfulness and harmlessness.
Outcome: The proposed method improves LLMs’ safety over all baselines.
Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems (2020.findings-emnlp)

Copied to clipboard

Challenge: Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress through using reinforcement learning methods.
Approach: They propose a dialogue action decoder and a simulator-free adversarial learning method to improve dialogue agent performance without using reinforcement learning.
Outcome: The proposed methods achieve more stable and higher performance with fewer efforts, such as the domain knowledge required to design a user simulator and the intractable parameter tuning in reinforcement learning.
One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for goal-oriented dialogues involve training separate models for specific combinations of objectives, leading to computational and scalability issues.
Approach: They propose a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining.
Outcome: The proposed method can adapt to varying objective preferences at inference time without retraining.
Better LLM Reasoning via Dual-Play (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have made remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR) however, external supervision remains a bottleneck for tasks and domains for which supervised data are scarce or non-existent.
Approach: They propose a novel dual-play framework that adversarially trains two models initialized from the same base model.
Outcome: The proposed framework improves the math reasoning performance of large language models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations