Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning

• URL: http://arxiv.org/abs/2410.16843v1
• Date: Tue, 22 Oct 2024 09:25:21 GMT
• Title: Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning
• Authors: Zongmeng Zhang, Yufeng Shi, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li,
• Abstract summary: We focus on the trustworthiness of language models with respect to retrieval augmentation. We deem that retrieval-augmented language models have the inherent capabilities of supplying response according to both contextual and parametric knowledge. Inspired by aligning language models with human preference, we take the first step towards aligning retrieval-augmented language models to a status where it responds relying merely on the external evidence.
• Score: 84.94709351266557
• License:
• Abstract: Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect to retrieval augmentation. Despite being supported with external evidence, retrieval-augmented generation still suffers from hallucinations, one primary cause of which is the conflict between contextual and parametric knowledge. We deem that retrieval-augmented language models have the inherent capabilities of supplying response according to both contextual and parametric knowledge. Inspired by aligning language models with human preference, we take the first step towards aligning retrieval-augmented language models to a status where it responds relying merely on the external evidence and disregards the interference of parametric knowledge. Specifically, we propose a reinforcement learning based algorithm Trustworthy-Alignment, theoretically and experimentally demonstrating large language models' capability of reaching a trustworthy status without explicit supervision on how to respond. Our work highlights the potential of large language models on exploring its intrinsic abilities by its own and expands the application scenarios of alignment from fulfilling human preference to creating trustworthy agents.

Related papers

• Proceedings of the First International Workshop on Next-Generation Language Models for Knowledge Representation and Reasoning (NeLaMKRR 2024) [16.282850445579857]
  Reasoning is an essential component of human intelligence as it plays a fundamental role in our ability to think critically. Recent leap forward in natural language processing, with the emergence of language models based on transformers, is hinting at the possibility that these models exhibit reasoning abilities. Despite ongoing discussions about what reasoning is in language models, it is still not easy to pin down to what extent these models are actually capable of reasoning.
  arXiv  Detail & Related papers  (2024-10-07T02:31:47Z)
• Language Models as Models of Language [0.0]
  This chapter critically examines the potential contributions of modern language models to theoretical linguistics. I review a growing body of empirical evidence suggesting that language models can learn hierarchical syntactic structure and exhibit sensitivity to various linguistic phenomena. I conclude that closer collaboration between theoretical linguists and computational researchers could yield valuable insights.
  arXiv  Detail & Related papers  (2024-08-13T18:26:04Z)
• On the application of Large Language Models for language teaching and assessment technology [18.735612275207853]
  We look at the potential for incorporating large language models in AI-driven language teaching and assessment systems. We find that larger language models offer improvements over previous models in text generation. For automated grading and grammatical error correction, tasks whose progress is checked on well-known benchmarks, early investigations indicate that large language models on their own do not improve on state-of-the-art results.
  arXiv  Detail & Related papers  (2023-07-17T11:12:56Z)
• Commonsense Knowledge Transfer for Pre-trained Language Models [83.01121484432801]
  We introduce commonsense knowledge transfer, a framework to transfer the commonsense knowledge stored in a neural commonsense knowledge model to a general-purpose pre-trained language model. It first exploits general texts to form queries for extracting commonsense knowledge from the neural commonsense knowledge model. It then refines the language model with two self-supervised objectives: commonsense mask infilling and commonsense relation prediction.
  arXiv  Detail & Related papers  (2023-06-04T15:44:51Z)
• Chain of Hindsight Aligns Language Models with Feedback [62.68665658130472]
  We propose a novel technique, Chain of Hindsight, that is easy to optimize and can learn from any form of feedback, regardless of its polarity. We convert all types of feedback into sequences of sentences, which are then used to fine-tune the model. By doing so, the model is trained to generate outputs based on feedback, while learning to identify and correct negative attributes or errors.
  arXiv  Detail & Related papers  (2023-02-06T10:28:16Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• LaMDA: Language Models for Dialog Applications [75.75051929981933]
  LaMDA is a family of Transformer-based neural language models specialized for dialog. Fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements.
  arXiv  Detail & Related papers  (2022-01-20T15:44:37Z)
• 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)
• The Rediscovery Hypothesis: Language Models Need to Meet Linguistics [8.293055016429863]
  We study whether linguistic knowledge is a necessary condition for good performance of modern language models. We show that language models that are significantly compressed but perform well on their pretraining objectives retain good scores when probed for linguistic structures. This result supports the rediscovery hypothesis and leads to the second contribution of our paper: an information-theoretic framework that relates language modeling objective with linguistic information.
  arXiv  Detail & Related papers  (2021-03-02T15:57:39Z)

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.