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

arXiv: https://arxiv.org/abs/2309.10015 · HTML: https://mlsanity.com/paper/2309.10015/

## Key facts

- Cited by 6 papers in the map (data through 14 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.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [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)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems](https://mlsanity.com/paper/1506.08909/) (2015)
- [DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension](https://mlsanity.com/paper/1902.00164/) (2019)
- [MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://mlsanity.com/paper/2004.04494/) (2020)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [Retrieve and Refine: Improved Sequence Generation Models For Dialogue](https://mlsanity.com/paper/1808.04776/) (2018)
- [TIMEDIAL: Temporal Commonsense Reasoning in Dialog](https://mlsanity.com/paper/2106.04571/) (2021)
- [Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1804.06512/) (2018)
- [CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues](https://mlsanity.com/paper/2203.13926/) (2022)
- [Commonsense-Focused Dialogues for Response Generation: An Empirical Study](https://mlsanity.com/paper/2109.06427/) (2021)
- [End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning](https://mlsanity.com/paper/1711.10712/) (2017)
- [Commonsense Reasoning for Conversational AI: A Survey of the State of the Art](https://mlsanity.com/paper/2302.07926/) (2023)
- [NaRLE: Natural Language Models using Reinforcement Learning with Emotion Feedback](https://mlsanity.com/paper/2110.02148/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Survey on Human Preference Learning for Large Language Models](https://mlsanity.com/paper/2406.11191/) (2024)
- [The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models](https://mlsanity.com/paper/2402.01874/) (2024)
- [A Survey on Progress in LLM Alignment from the Perspective of Reward Design](https://mlsanity.com/paper/2505.02666/) (2025)
- [iTBLS: A Dataset of Interactive Conversations Over Tabular Information](https://mlsanity.com/paper/2404.12580/) (2024)
- [FLEx: Language Modeling with Few-shot Language Explanations](https://mlsanity.com/paper/2601.04157/) (2026)
- [Commonsense Generation and Evaluation for Dialogue Systems using Large Language Models](https://mlsanity.com/paper/2506.19483/) (2025)

## 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.