Crystal: Introspective Reasoners Reinforced with Self-Feedback

• URL: http://arxiv.org/abs/2310.04921v2
• Date: Wed, 18 Oct 2023 14:52:03 GMT
• Title: Crystal: Introspective Reasoners Reinforced with Self-Feedback
• Authors: Jiacheng Liu, Ramakanth Pasunuru, Hannaneh Hajishirzi, Yejin Choi, Asli Celikyilmaz
• Abstract summary: We propose a novel method to develop an introspective commonsense reasoner, Crystal. To tackle commonsense problems, it first introspects for knowledge statements related to the given question, and subsequently makes an informed prediction that is grounded in the previously introspected knowledge. Experiments show that Crystal significantly outperforms both the standard supervised finetuning and chain-of-thought distilled methods, and enhances the transparency of the commonsense reasoning process.
• Score: 118.53428015478957
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Extensive work has shown that the performance and interpretability of commonsense reasoning can be improved via knowledge-augmented reasoning methods, where the knowledge that underpins the reasoning process is explicitly verbalized and utilized. However, existing implementations, including "chain-of-thought" and its variants, fall short in capturing the introspective nature of knowledge required in commonsense reasoning, and in accounting for the mutual adaptation between the generation and utilization of knowledge. We propose a novel method to develop an introspective commonsense reasoner, Crystal. To tackle commonsense problems, it first introspects for knowledge statements related to the given question, and subsequently makes an informed prediction that is grounded in the previously introspected knowledge. The knowledge introspection and knowledge-grounded reasoning modes of the model are tuned via reinforcement learning to mutually adapt, where the reward derives from the feedback given by the model itself. Experiments show that Crystal significantly outperforms both the standard supervised finetuning and chain-of-thought distilled methods, and enhances the transparency of the commonsense reasoning process. Our work ultimately validates the feasibility and potential of reinforcing a neural model with self-feedback.

Related papers

• RECKONING: Reasoning through Dynamic Knowledge Encoding [51.076603338764706]
  We show that language models can answer questions by reasoning over knowledge provided as part of the context. In these situations, the model fails to distinguish the knowledge that is necessary to answer the question. We propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model's parameters.
  arXiv  Detail & Related papers  (2023-05-10T17:54:51Z)
• Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation [45.95864432188745]
  Recent advances in large-scale pre-training provide large models with the potential to learn knowledge from the raw text. We propose various methods that best elicit knowledge from large models. Our human study indicates that, though hallucinations exist, large models post the unique advantage of being able to output common sense.
  arXiv  Detail & Related papers  (2022-11-03T04:48:38Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA [67.75989848202343]
  This paper presents a unified end-to-end retriever-reader framework towards knowledge-based VQA. We shed light on the multi-modal implicit knowledge from vision-language pre-training models to mine its potential in knowledge reasoning. Our scheme is able to not only provide guidance for knowledge retrieval, but also drop these instances potentially error-prone towards question answering.
  arXiv  Detail & Related papers  (2022-06-30T02:35:04Z)
• KAT: A Knowledge Augmented Transformer for Vision-and-Language [56.716531169609915]
  We propose a novel model - Knowledge Augmented Transformer (KAT) - which achieves a strong state-of-the-art result on the open-domain multimodal task of OK-VQA. Our approach integrates implicit and explicit knowledge in an end to end encoder-decoder architecture, while still jointly reasoning over both knowledge sources during answer generation. An additional benefit of explicit knowledge integration is seen in improved interpretability of model predictions in our analysis.
  arXiv  Detail & Related papers  (2021-12-16T04:37:10Z)
• Generated Knowledge Prompting for Commonsense Reasoning [53.88983683513114]
  We propose generating knowledge statements directly from a language model with a generic prompt format. This approach improves performance of both off-the-shelf and finetuned language models on four commonsense reasoning tasks. Notably, we find that a model's predictions can improve when using its own generated knowledge.
  arXiv  Detail & Related papers  (2021-10-15T21:58:03Z)
• Entity-Based Knowledge Conflicts in Question Answering [29.973926661540524]
  We formalize the problem of knowledge conflicts, where the contextual information contradicts the learned information. We propose a method to mitigate over-reliance on parametric knowledge, which minimizes hallucination, and improves out-of-distribution generalization by 4%-7%. Our findings demonstrate the importance for practitioners to evaluate model tendency to hallucinate rather than read, and show that our mitigation strategy encourages generalization to evolving information.
  arXiv  Detail & Related papers  (2021-09-10T18:29:44Z)
• Social Commonsense Reasoning with Multi-Head Knowledge Attention [24.70946979449572]
  Social Commonsense Reasoning requires understanding of text, knowledge about social events and their pragmatic implications, as well as commonsense reasoning skills. We propose a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell.
  arXiv  Detail & Related papers  (2020-10-12T10:24:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.