Fine-tuning Language Models for Factuality

• URL: http://arxiv.org/abs/2311.08401v1
• Date: Tue, 14 Nov 2023 18:59:15 GMT
• Title: Fine-tuning Language Models for Factuality
• Authors: Katherine Tian and Eric Mitchell and Huaxiu Yao and Christopher D. Manning and Chelsea Finn
• Abstract summary: Large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations' In this work, we fine-tune language models to be more factual, without human labeling.
• Score: 96.5203774943198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The fluency and creativity of large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations.' These errors can inadvertently spread misinformation or harmfully perpetuate misconceptions. Further, manual fact-checking of model responses is a time-consuming process, making human factuality labels expensive to acquire. In this work, we fine-tune language models to be more factual, without human labeling and targeting more open-ended generation settings than past work. We leverage two key recent innovations in NLP to do so. First, several recent works have proposed methods for judging the factuality of open-ended text by measuring consistency with an external knowledge base or simply a large model's confidence scores. Second, the direct preference optimization algorithm enables straightforward fine-tuning of language models on objectives other than supervised imitation, using a preference ranking over possible model responses. We show that learning from automatically generated factuality preference rankings, generated either through existing retrieval systems or our novel retrieval-free approach, significantly improves the factuality (percent of generated claims that are correct) of Llama-2 on held-out topics compared with RLHF or decoding strategies targeted at factuality. At 7B scale, compared to Llama-2-chat, we observe 58% and 40% reduction in factual error rate when generating biographies and answering medical questions, respectively.

Related papers

• Are We Falling in a Middle-Intelligence Trap? An Analysis and Mitigation of the Reversal Curse [73.65112477688353]
  Recent studies have highlighted a phenomenon in large language models known as "the reversal curse" We contend that the reversal curse is partially a result of specific model training objectives. We propose a novel training method, BI Casual language modeling Optimization (BICO), designed to mitigate the reversal curse.
  arXiv  Detail & Related papers  (2023-11-13T17:01:12Z)
• Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models [39.37532848489779]
  We propose Error Norm Truncation (ENT), a robust enhancement method to the standard training objective that truncates noisy data. We show that ENT improves generation quality over standard training and previous soft and hard truncation methods.
  arXiv  Detail & Related papers  (2023-10-02T01:30:27Z)
• Training Language Models with Language Feedback at Scale [50.70091340506957]
  We introduce learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning the language model on the input, an initial LM output, and feedback to generate refinements. We show theoretically that ILF can be viewed as Bayesian Inference, similar to Reinforcement Learning from human feedback.
  arXiv  Detail & Related papers  (2023-03-28T17:04:15Z)
• mFACE: Multilingual Summarization with Factual Consistency Evaluation [79.60172087719356]
  Abstractive summarization has enjoyed renewed interest in recent years, thanks to pre-trained language models and the availability of large-scale datasets. Despite promising results, current models still suffer from generating factually inconsistent summaries. We leverage factual consistency evaluation models to improve multilingual summarization.
  arXiv  Detail & Related papers  (2022-12-20T19:52:41Z)
• Internet-augmented language models through few-shot prompting for open-domain question answering [6.573232954655063]
  We capitalize on the unique few-shot capabilities offered by large-scale language models to overcome some of their challenges. We use few-shot prompting to learn to condition language models on information returned from the web using Google Search. We find that language models conditioned on the web surpass performance of closed-book models of similar, or even larger, model sizes in open-domain question answering.
  arXiv  Detail & Related papers  (2022-03-10T02:24:14Z)
• Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition [80.446770909975]
  Linguistic knowledge is of great benefit to scene text recognition. How to effectively model linguistic rules in end-to-end deep networks remains a research challenge. We propose an autonomous, bidirectional and iterative ABINet for scene text recognition.
  arXiv  Detail & Related papers  (2021-03-11T06:47:45Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• Analysis of Predictive Coding Models for Phonemic Representation Learning in Small Datasets [0.0]
  The present study investigates the behaviour of two predictive coding models, Autoregressive Predictive Coding and Contrastive Predictive Coding, in a phoneme discrimination task. Our experiments show a strong correlation between the autoregressive loss and the phoneme discrimination scores with the two datasets. The CPC model shows rapid convergence already after one pass over the training data, and, on average, its representations outperform those of APC on both languages.
  arXiv  Detail & Related papers  (2020-07-08T15:46:13Z)

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.