RankGen: Improving Text Generation with Large Ranking Models

• URL: http://arxiv.org/abs/2205.09726v1
• Date: Thu, 19 May 2022 17:36:46 GMT
• Title: RankGen: Improving Text Generation with Large Ranking Models
• Authors: Kalpesh Krishna, Yapei Chang, John Wieting, Mohit Iyyer
• Abstract summary: RankGen is an encoder model that scores generations given a prefix. It can be flexibly incorporated as a scoring function in beam search. We show that RankGen significantly outperforms decoding algorithms like nucleus, top-k, and typical sampling.
• Score: 43.448251157355784
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To address these issues, we present RankGen, an encoder model (1.2B parameters) that scores model generations given a prefix. RankGen can be flexibly incorporated as a scoring function in beam search and used to decode from any pretrained language model. We train RankGen using large-scale contrastive learning to map a prefix close to the ground-truth sequence that follows it and far away from two types of negatives: (1) random sequences from the same document as the prefix, and, which discourage topically-similar but irrelevant generations; (2) sequences generated from a large language model conditioned on the prefix, which discourage repetition and hallucination. Experiments across four different language models (345M-11B parameters) and two domains show that RankGen significantly outperforms decoding algorithms like nucleus, top-k, and typical sampling on both automatic metrics (85.0 vs 77.3 MAUVE) as well as human evaluations with English writers (74.5% human preference over nucleus sampling). Analysis reveals that RankGen outputs are more relevant to the prefix and improve continuity and coherence compared to baselines. We open source our model checkpoints, code, and human preferences with detailed explanations for future research.

Related papers

• Benchmarking Large Language Models with Integer Sequence Generation Tasks [1.3108652488669736]
  This paper presents a novel benchmark where the large language model (LLM) must write code that computes integer sequences from the Online Encyclopedia of Sequences (OEIS) Our benchmark reveals that the o1 series of models outperform other frontier models from OpenAI, Anthropic, Meta, and Google in accuracy and cheating rates across both easy and hard integer sequences.
  arXiv  Detail & Related papers  (2024-11-07T02:05:43Z)
• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• Inflected Forms Are Redundant in Question Generation Models [27.49894653349779]
  We propose an approach to enhance the performance of Question Generation using an encoder-decoder framework. Firstly, we identify the inflected forms of words from the input of encoder, and replace them with the root words. Secondly, we propose to adapt QG as a combination of the following actions in the encode-decoder framework: generating a question word, copying a word from the source sequence or generating a word transformation type.
  arXiv  Detail & Related papers  (2023-01-01T13:08:11Z)
• CodeExp: Explanatory Code Document Generation [94.43677536210465]
  Existing code-to-text generation models produce only high-level summaries of code. We conduct a human study to identify the criteria for high-quality explanatory docstring for code. We present a multi-stage fine-tuning strategy and baseline models for the task.
  arXiv  Detail & Related papers  (2022-11-25T18:05:44Z)
• A Non-monotonic Self-terminating Language Model [62.93465126911921]
  In this paper, we focus on the problem of non-terminating sequences resulting from an incomplete decoding algorithm. We first define an incomplete probable decoding algorithm which includes greedy search, top-$k$ sampling, and nucleus sampling. We then propose a non-monotonic self-terminating language model, which relaxes the constraint of monotonically increasing termination probability.
  arXiv  Detail & Related papers  (2022-10-03T00:28:44Z)
• Twist Decoding: Diverse Generators Guide Each Other [116.20780037268801]
  We introduce Twist decoding, a simple and general inference algorithm that generates text while benefiting from diverse models. Our method does not assume the vocabulary, tokenization or even generation order is shared.
  arXiv  Detail & Related papers  (2022-05-19T01:27:53Z)
• Massive-scale Decoding for Text Generation using Lattices [34.2658286826597]
  We present a search algorithm to construct lattices encoding a massive number of generation options. We show that our algorithm encodes hundreds to thousands of diverse options that remain grammatical and high-quality into one linear-sized lattice.
  arXiv  Detail & Related papers  (2021-12-14T18:56:11Z)
• Unsupervised and Distributional Detection of Machine-Generated Text [1.552214657968262]
  The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. We propose a method to detect those machine-generated documents leveraging repeated higher-order n-grams. Our experiments show that leveraging that signal allows us to rank suspicious documents accurately.
  arXiv  Detail & Related papers  (2021-11-04T14:07:46Z)
• On the Discrepancy between Density Estimation and Sequence Generation [92.70116082182076]
  log-likelihood is highly correlated with BLEU when we consider models within the same family. We observe no correlation between rankings of models across different families.
  arXiv  Detail & Related papers  (2020-02-17T20:13:35Z)

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.