# AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies

arXiv: https://arxiv.org/abs/2211.12615 · HTML: https://mlsanity.com/paper/2211.12615/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [Unsupervised Evaluation of Interactive Dialog with DialoGPT](https://mlsanity.com/paper/2006.12719/) (2020)
- [Dialogue Natural Language Inference](https://mlsanity.com/paper/1811.00671/) (2018)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling](https://mlsanity.com/paper/2012.13391/) (2020)
- [Modeling Strong and Human-Like Gameplay with KL-Regularized Search](https://mlsanity.com/paper/2112.07544/) (2021)
- [Human-Level Performance in No-Press Diplomacy via Equilibrium Search](https://mlsanity.com/paper/2010.02923/) (2020)
- [No Press Diplomacy: Modeling Multi-Agent Gameplay](https://mlsanity.com/paper/1909.02128/) (2019)
- [No-Press Diplomacy from Scratch](https://mlsanity.com/paper/2110.02924/) (2021)
- [Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration](https://mlsanity.com/paper/2012.15375/) (2020)
- [Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game](https://mlsanity.com/paper/1506.04744/) (2015)

## Built on by (most cited first, 2 of 2)

- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Grounding Language Models to Images for Multimodal Inputs and Outputs](https://mlsanity.com/paper/2301.13823/) (2023)

## Abstract (arXiv)

Existing approaches built separate classifiers to detect nonsense in dialogues. In this paper, we show that without external classifiers, dialogue models can detect errors in their own messages introspectively, by calculating the likelihood of replies that are indicative of poor messages. For example, if an agent believes its partner is likely to respond "I don't understand" to a candidate message, that message may not make sense, so an alternative message should be chosen. We evaluate our approach on a dataset from the game Diplomacy, which contains long dialogues richly grounded in the game state, on which existing models make many errors. We first show that hand-crafted replies can be effective for the task of detecting nonsense in applications as complex as Diplomacy. We then design AutoReply, an algorithm to search for such discriminative replies automatically, given a small number of annotated dialogue examples. We find that AutoReply-generated replies outperform handcrafted replies and perform on par with carefully fine-tuned large supervised models. Results also show that one single reply without much computation overheads can also detect dialogue nonsense reasonably well.