# Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue

arXiv: https://arxiv.org/abs/2311.07445 · HTML: https://mlsanity.com/paper/2311.07445/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 38 of its 57 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Placed in

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

## Builds on (most cited first, 30 of 38)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [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)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts](https://mlsanity.com/paper/2305.13300/) (2023)
- [Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision](https://mlsanity.com/paper/2305.03047/) (2023)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [Knowledge-Grounded Dialogue Generation with Pre-trained Language Models](https://mlsanity.com/paper/2010.08824/) (2020)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [Scaling Transformer to 1M tokens and beyond with RMT](https://mlsanity.com/paper/2304.11062/) (2023)
- [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019)
- [Few-Shot Text Generation with Pattern-Exploiting Training](https://mlsanity.com/paper/2012.11926/) (2020)
- [Improving Language Models via Plug-and-Play Retrieval Feedback](https://mlsanity.com/paper/2305.14002/) (2023)
- [PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning](https://mlsanity.com/paper/2006.16779/) (2020)
- [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://mlsanity.com/paper/1911.02707/) (2019)
- [DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances](https://mlsanity.com/paper/2012.01775/) (2020)
- [Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading](https://mlsanity.com/paper/1906.02738/) (2019)
- [Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation](https://mlsanity.com/paper/2110.08501/) (2021)

## Built on by (most cited first, 11 of 11)

- [PonderLM: Pretraining Language Models to Ponder in Continuous Space](https://mlsanity.com/paper/2505.20674/) (2025)
- [IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues](https://mlsanity.com/paper/2405.13021/) (2024)
- [Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation](https://mlsanity.com/paper/2404.09043/) (2024)
- [Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Training](https://mlsanity.com/paper/2506.00386/) (2025)
- [Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies](https://mlsanity.com/paper/2603.23406/) (2026)
- [A Fully Automated Pipeline for Conversational Discourse Annotation: Tree Scheme Generation and Labeling with Large Language Models](https://mlsanity.com/paper/2504.08961/) (2025)
- [Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling](https://mlsanity.com/paper/2508.16876/) (2025)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [CAST: Achieving Stable LLM-based Text Analysis for Data Analytics](https://mlsanity.com/paper/2602.15861/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)
- [ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents](https://mlsanity.com/paper/2608.21969/) (2026)

## Abstract (arXiv)

The emergence of large language models (LLMs) further improves the capabilities of open-domain dialogue systems and can generate fluent, coherent, and diverse responses. However, LLMs still lack a crucial ability: communication skills. This limitation renders them more like information seeking tools rather than anthropomorphic chatbots. Communication skills, such as topic transition, proactively asking questions, concept guidance, empathy, and summarising often should be taken into consideration, to make LLMs more anthropomorphic and proactive during the conversation, thereby increasing the interest of users and attracting them to chat for longer. However, enabling these communication skills in black-box LLMs remains a key challenge because they do not have the same utterance formation mode as real people: think before speaking. Inspired by linguistics and cognitive science, we empower LLMs with communication skills through inner monologues. To evaluate various communication skills, we construct a benchmark named Cskills, which can also more comprehensively evaluate the dialogue generation ability of the model. Experimental results show that the proposed CSIM strategy improves the backbone models and outperforms the baselines.