Offline RL for Natural Language Generation with Implicit Language Q Learning

• URL: http://arxiv.org/abs/2206.11871v2
• Date: Mon, 1 May 2023 04:42:27 GMT
• Title: Offline RL for Natural Language Generation with Implicit Language Q Learning
• Authors: Charlie Snell, Ilya Kostrikov, Yi Su, Mengjiao Yang, Sergey Levine
• Abstract summary: Large language models can be inconsistent when it comes to completing user specified tasks. We propose a novel RL method, that combines both the flexible utility framework of RL with the ability of supervised learning. In addition to empirically validating ILQL, we present a detailed empirical analysis situations where offline RL can be useful in natural language generation settings.
• Score: 87.76695816348027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models distill broad knowledge from text corpora. However, they can be inconsistent when it comes to completing user specified tasks. This issue can be addressed by finetuning such models via supervised learning on curated datasets, or via reinforcement learning. In this work, we propose a novel offline RL method, implicit language Q-learning (ILQL), designed for use on language models, that combines both the flexible utility maximization framework of RL algorithms with the ability of supervised learning to leverage previously collected data, as well as its simplicity and stability. Our method employs a combination of value conservatism alongside an implicit dataset support constraint in learning value functions, which are then used to guide language model generations towards maximizing user-specified utility functions. In addition to empirically validating ILQL, we present a detailed empirical analysis of situations where offline RL can be useful in natural language generation settings, demonstrating how it can be a more effective utility optimizer than prior approaches for end-to-end dialogue, and how it can effectively optimize high variance reward functions based on subjective judgement, such as whether to label a comment as toxic or not.

Related papers

• Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation [2.9921619703037274]
  We propose a retrieval augmented generation (RAG) framework backed by a large language model (LLM) to correct the output of a smaller model for the linguistic task of morphological glossing. We leverage linguistic information to make up for the lack of data and trainable parameters, while allowing for inputs from written descriptive grammars interpreted and distilled through an LLM. We show that a compact, RAG-supported model is highly effective in data-scarce settings, achieving a new state-of-the-art for this task and our target languages.
  arXiv  Detail & Related papers  (2024-10-01T04:20:14Z)
• Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning [53.241569810013836]
  We propose a new framework based on large language models (LLMs) and decision Tree reasoning (OCTree) Our key idea is to leverage LLMs' reasoning capabilities to find good feature generation rules without manually specifying the search space. Our empirical results demonstrate that this simple framework consistently enhances the performance of various prediction models.
  arXiv  Detail & Related papers  (2024-06-12T08:31:34Z)
• CLAIM Your Data: Enhancing Imputation Accuracy with Contextual Large Language Models [0.18416014644193068]
  This paper introduces the Contextual Language model for Accurate Imputation Method (CLAIM) Unlike traditional imputation methods, CLAIM utilizes contextually relevant natural language descriptors to fill missing values. Our evaluations across diverse datasets and missingness patterns reveal CLAIM's superior performance over existing imputation techniques.
  arXiv  Detail & Related papers  (2024-05-28T00:08:29Z)
• RecExplainer: Aligning Large Language Models for Explaining Recommendation Models [50.74181089742969]
  Large language models (LLMs) have demonstrated remarkable intelligence in understanding, reasoning, and instruction following. This paper presents the initial exploration of using LLMs as surrogate models to explain black-box recommender models. To facilitate an effective alignment, we introduce three methods: behavior alignment, intention alignment, and hybrid alignment.
  arXiv  Detail & Related papers  (2023-11-18T03:05:43Z)
• Instructed Language Models with Retrievers Are Powerful Entity Linkers [87.16283281290053]
  Instructed Generative Entity Linker (INSGENEL) is the first approach that enables casual language models to perform entity linking over knowledge bases. INSGENEL outperforms previous generative alternatives with +6.8 F1 points gain on average.
  arXiv  Detail & Related papers  (2023-11-06T16:38:51Z)
• Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization [73.74371798168642]
  We introduce an open-source modular library, RL4LMs, for optimizing language generators with reinforcement learning. Next, we present the GRUE benchmark, a set of 6 language generation tasks which are supervised not by target strings, but by reward functions. Finally, we introduce an easy-to-use, performant RL algorithm, NLPO, that learns to effectively reduce the action space in language generation.
  arXiv  Detail & Related papers  (2022-10-03T21:38:29Z)
• Learning Natural Language Generation from Scratch [25.984828046001013]
  This paper introduces TRUncated ReinForcement Learning for Language (TrufLL) It is an original ap-proach to train conditional language models from scratch by only using reinforcement learning (RL)
  arXiv  Detail & Related papers  (2021-09-20T08:46:51Z)
• Efficient Nearest Neighbor Language Models [114.40866461741795]
  Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore. We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
  arXiv  Detail & Related papers  (2021-09-09T12:32:28Z)
• Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning [30.5853328612593]
  In this work, we explore fine-tuning methods of BERT -- a pre-trained Transformer based language model. Our experimental results show an advantage in model performance by maximizing the approximate knowledge gain of the model. We analyze the benefits of freezing layers of the language model during fine-tuning to reduce the number of trainable parameters.
  arXiv  Detail & Related papers  (2020-12-04T08:34:39Z)

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.