mlsanityData to 7 Oct 2026

SYNDICOM: Improving Conversational Commonsense with Error-Injection and Natural Language Feedback

arXiv 2309.10015 ↗First posted 18 Sep 2023cs.CL cs.AI cs.LGcited by 6

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Commonsense reasoning is a critical aspect of human communication. Despite recent advances in conversational AI driven by large language models, commonsense reasoning remains a challenging task. In this work, we introduce SYNDICOM - a method for improving commonsense in dialogue response generation. SYNDICOM consists of two components. The first component is a dataset composed of commonsense dialogues created from a knowledge graph and synthesized into natural language. This dataset includes both valid and invalid responses to dialogue contexts, along with natural language feedback (NLF) for the invalid responses. The second contribution is a two-step procedure: training a model to predict natural language feedback (NLF) for invalid responses, and then training a response generation model conditioned on the predicted NLF, the invalid response, and the dialogue. SYNDICOM is scalable and does not require reinforcement learning. Empirical results on three tasks are evaluated using a broad range of metrics. SYNDICOM achieves a relative improvement of 53% over ChatGPT on ROUGE1, and human evaluators prefer SYNDICOM over ChatGPT 57% of the time. We will publicly release the code and the full dataset.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 23 of its 30 references that are in the map. First posted on arXiv 18 Sep 2023.

Builds on

23 of 30 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Art15 Feb

Other references · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  7. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  8. 2022Self-critiquing models for assisting human evaluatorscited by 372
  9. 2022Generating Sequences by Learning to Self-Correctcited by 271
  10. 2020COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphscited by 254
  11. 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
  12. 2019DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehensioncited by 156
10 more
  1. 2020MuTual: A Dataset for Multi-Turn Dialogue Reasoningcited by 114
  2. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
  3. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 92
  4. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  5. 2021TIMEDIAL: Temporal Commonsense Reasoning in Dialogcited by 55
  6. 2018Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systemscited by 53
  7. 2022CICERO: A Dataset for Contextualized Commonsense Inference in Dialoguescited by 38
  8. 2021Commonsense-Focused Dialogues for Response Generation: An Empirical Studycited by 30
  9. 2017End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learningcited by 19
  10. 2021NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedbackcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024A Survey on Human Preference Learning for Large Language Modelscited by 23
  2. 2024The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Modelscited by 15
  3. 2025A Survey on Progress in LLM Alignment from the Perspective of Reward Designcited by 15
  4. 2024iTBLS: A Dataset of Interactive Conversations Over Tabular Informationcited by 3
  5. 2026FLEx: Language Modeling with Few-shot Language Explanationscited by 1
  6. 2025Commonsense Generation and Evaluation for Dialogue Systems using Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI
  2. 2024Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models
  3. 2023Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
  4. 2023ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
  5. 2023CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models
  6. 2026Synthetic Data Generation for Training Diversified Commonsense Reasoning Models
  7. 2022DiscoSense: Commonsense Reasoning with Discourse Connectives
  8. 2024SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation