Data to 14 Oct 2026

Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents

arXiv 2310.09343 ↗First posted 13 Oct 2023cs.CL cs.AIcited by 41

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 1 more

LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Human-like chatbots necessitate the use of commonsense reasoning in order to effectively comprehend and respond to implicit information present within conversations. Achieving such coherence and informativeness in responses, however, is a non-trivial task. Even for large language models (LLMs), the task of identifying and aggregating key evidence within a single hop presents a substantial challenge. This complexity arises because such evidence is scattered across multiple turns in a conversation, thus necessitating integration over multiple hops. Hence, our focus is to facilitate such multi-hop reasoning over a dialogue context, namely dialogue chain-of-thought (CoT) reasoning. To this end, we propose a knowledge distillation framework that leverages LLMs as unreliable teachers and selectively distills consistent and helpful rationales via alignment filters. We further present DOCTOR, a DialOgue Chain-of-ThOught Reasoner that provides reliable CoT rationales for response generation. We conduct extensive experiments to show that enhancing dialogue agents with high-quality rationales from DOCTOR significantly improves the quality of their responses.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 33 of its 43 references that are in the map. First posted on arXiv 13 Oct 2023.

Builds on

33 of 43 references.

Closest ancestors · 2

Same direction, newest first

Other references · 31

2020Language Models are Few-Shot Learnerscited by 32,419
2022Training language models to follow instructions with human feedbackcited by 15,971
2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 652
2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 353
2021Symbolic Knowledge Distillation: from General Language Models to Commonsense Modelscited by 270

19 more

2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
2021Generated Knowledge Prompting for Commonsense Reasoningcited by 214
2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 168
2020Unsupervised Commonsense Question Answering with Self-Talkcited by 161
2022Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanationscited by 159
2019DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehensioncited by 156
2020MuTual: A Dataset for Multi-Turn Dialogue Reasoningcited by 115
2023SCOTT: Self-Consistent Chain-of-Thought Distillationcited by 105
2023Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Taskscited by 64
2022CICERO: A Dataset for Contextualized Commonsense Inference in Dialoguescited by 38
2021Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generationcited by 26
2021Topic-Aware Contrastive Learning for Abstractive Dialogue Summarizationcited by 23
2022Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Qualitycited by 22
2020CARE: Commonsense-Aware Emotional Response Generation with Latent Conceptscited by 20
2022Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarizationcited by 14
2022Multiview Contextual Commonsense Inference: A New Dataset and Taskcited by 11
2022ComFact: A Benchmark for Linking Contextual Commonsense Knowledgecited by 11
2021Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rulescited by 9
2022Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue Comprehensioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 21; 2025: 13; 2026: 5.

41 papers.

Sort:

By area:

2024LLM Inference Unveiled: Survey and Roofline Model Insightscited by 152
2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
2024The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Modelscited by 93
2024Model Compression and Efficient Inference for Large Language Models: A Surveycited by 64
2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 57
2024Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Applicationcited by 56
2024Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversationcited by 55
2024Towards Lifelong Dialogue Agents via Timeline-based Memory Managementcited by 51
2024ESCoT: Towards Interpretable Emotional Support Dialogue Systemscited by 46
2024From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Modelscited by 43
2024CodeAgent: Autonomous Communicative Agents for Code Reviewcited by 34
2025Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learningcited by 27

29 more

Similar, not cited

Close in wording, no citation either way