# Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models

arXiv: https://arxiv.org/abs/2305.17878 · HTML: https://mlsanity.com/paper/2305.17878/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 39 of its 66 references that are in the map.
- First posted on arXiv 29 May 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 39)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Towards Emotional Support Dialog Systems](https://mlsanity.com/paper/2106.01144/) (2021)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Beyond Goldfish Memory: Long-Term Open-Domain Conversation](https://mlsanity.com/paper/2107.07567/) (2021)
- [Internet-Augmented Dialogue Generation](https://mlsanity.com/paper/2107.07566/) (2021)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Reframing Instructional Prompts to GPTk's Language](https://mlsanity.com/paper/2109.07830/) (2021)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [Key-Value Retrieval Networks for Task-Oriented Dialogue](https://mlsanity.com/paper/1705.05414/) (2017)
- [Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills](https://mlsanity.com/paper/2004.08449/) (2020)
- [Human-centric Dialog Training via Offline Reinforcement Learning](https://mlsanity.com/paper/2010.05848/) (2020)

## Built on by (most cited first, 30 of 31)

- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [AGILE: A Novel Reinforcement Learning Framework of LLM Agents](https://mlsanity.com/paper/2405.14751/) (2024)
- [Large Language Models in Mental Health Care: a Scoping Review](https://mlsanity.com/paper/2401.02984/) (2024)
- [Planning Like Human: A Dual-process Framework for Dialogue Planning](https://mlsanity.com/paper/2406.05374/) (2024)
- [Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges](https://mlsanity.com/paper/2403.02990/) (2024)
- [Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond](https://mlsanity.com/paper/2310.05317/) (2023)
- [Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation](https://mlsanity.com/paper/2403.06769/) (2024)
- [PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agents](https://mlsanity.com/paper/2509.17459/) (2025)
- [Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues](https://mlsanity.com/paper/2412.14584/) (2024)
- [TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking](https://mlsanity.com/paper/2502.11187/) (2025)
- [Dialogue Systems for Emotional Support via Value Reinforcement](https://mlsanity.com/paper/2501.17182/) (2025)
- [Script-Based Dialog Policy Planning for LLM-Powered Conversational Agents: A Basic Architecture for an "AI Therapist"](https://mlsanity.com/paper/2412.15242/) (2024)
- [Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planning](https://mlsanity.com/paper/2504.13643/) (2025)
- [MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue](https://mlsanity.com/paper/2502.19860/) (2025)
- ["I Like Sunnie More Than I Expected!": Exploring User Expectation and Perception of an Anthropomorphic LLM-based Conversational Agent for Well-Being Support](https://mlsanity.com/paper/2405.13803/) (2024)
- [Towards Open-Ended Emotional Support Conversations in LLMs via Reinforcement Learning with Future-Oriented Rewards](https://mlsanity.com/paper/2508.12935/) (2025)
- [DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors](https://mlsanity.com/paper/2505.17795/) (2025)
- [EmoFSM: A Finite State Machine for Emotional Support Conversation](https://mlsanity.com/paper/2504.11837/) (2025)
- [DiagGPT: An LLM-based and Multi-agent Dialogue System with Automatic Topic Management for Flexible Task-Oriented Dialogue](https://mlsanity.com/paper/2308.08043/) (2023)
- [SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events](https://mlsanity.com/paper/2408.05793/) (2024)
- [Somatic in the East, Psychological in the West?: Investigating Clinically-Grounded Cross-Cultural Depression Symptom Expression in LLMs](https://mlsanity.com/paper/2508.03247/) (2025)
- [Responsible Evaluation of AI for Mental Health](https://mlsanity.com/paper/2602.00065/) (2026)
- [A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks](https://mlsanity.com/paper/2511.21706/) (2025)
- [Everyone is unique: Towards Behaviorally Heterogeneous Negotiation Dialogue Systems for Debt Collection](https://mlsanity.com/paper/2607.25218/) (2026)
- [Planning with Diffusion Models for Target-Oriented Dialogue Systems](https://mlsanity.com/paper/2504.16858/) (2025)
- [The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation](https://mlsanity.com/paper/2602.01598/) (2026)
- [EmoLLM: Appraisal-Grounded Cognitive-Emotional Co-Reasoning in Large Language Models](https://mlsanity.com/paper/2603.16553/) (2026)
- [PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues](https://mlsanity.com/paper/2604.18354/) (2026)
- [UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems](https://mlsanity.com/paper/2606.13683/) (2026)
- [Proactive Dialogue Policy Optimization via Cognitive-State Transition](https://mlsanity.com/paper/2609.34948/) (2026)

## Abstract (arXiv)

Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the "Ask an Expert" framework in which the model is trained with access to an "expert" which it can consult at each turn. Advice is solicited via a structured dialogue with the expert, and the model is optimized to selectively utilize (or ignore) it given the context and dialogue history. In this work the expert takes the form of an LLM. We evaluate this framework in a mental health support domain, where the structure of the expert conversation is outlined by pre-specified prompts which reflect a reasoning strategy taught to practitioners in the field. Blenderbot models utilizing "Ask an Expert" show quality improvements across all expert sizes, including those with fewer parameters than the dialogue model itself. Our best model provides a ~ 10% improvement over baselines, approaching human-level scores on "engingingness" and "helpfulness" metrics.