Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models

• URL: http://arxiv.org/abs/2410.15116v1
• Date: Sat, 19 Oct 2024 13:59:48 GMT
• Title: Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
• Authors: Qitan Lv, Jie Wang, Hanzhu Chen, Bin Li, Yongdong Zhang, Feng Wu,
• Abstract summary: COFT is a novel method to focus on different-level key texts, thereby avoiding getting lost in lengthy contexts. Experiments on the knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over $30%$ in the F1 score metric.
• Score: 58.952782707682815
• License:
• Abstract: Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM) -- which enhances models with up-to-date knowledge -- emerges as a promising method to reduce hallucination. However, existing RALMs may instead exacerbate hallucination when retrieving lengthy contexts. To address this challenge, we propose COFT, a novel \textbf{CO}arse-to-\textbf{F}ine highligh\textbf{T}ing method to focus on different granularity-level key texts, thereby avoiding getting lost in lengthy contexts. Specifically, COFT consists of three components: \textit{recaller}, \textit{scorer}, and \textit{selector}. First, \textit{recaller} applies a knowledge graph to extract potential key entities in a given context. Second, \textit{scorer} measures the importance of each entity by calculating its contextual weight. Finally, \textit{selector} selects high contextual weight entities with a dynamic threshold algorithm and highlights the corresponding paragraphs, sentences, or words in a coarse-to-fine manner. Extensive experiments on the knowledge hallucination benchmark demonstrate the effectiveness of COFT, leading to a superior performance over $30\%$ in the F1 score metric. Moreover, COFT also exhibits remarkable versatility across various long-form tasks, such as reading comprehension and question answering.

Related papers

• Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling [22.107187408777726]
  Hallucination detections for text generation with open-ended answers are more challenging. Recent studies on detecting hallucinations in long text without external resources conduct consistency comparison. We propose a graph-based context-aware (GCA) hallucination detection for text generations.
  arXiv  Detail & Related papers  (2024-09-17T15:38:36Z)
• Hallucination Augmented Contrastive Learning for Multimodal Large Language Model [53.65682783591723]
  Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend to generate erroneous or fabricated information. In this paper, we address hallucinations in MLLMs from a novel perspective of representation learning.
  arXiv  Detail & Related papers  (2023-12-12T04:05:15Z)
• Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus [99.33091772494751]
  Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields. LLMs are prone to hallucinate untruthful or nonsensical outputs that fail to meet user expectations. We propose a novel reference-free, uncertainty-based method for detecting hallucinations in LLMs.
  arXiv  Detail & Related papers  (2023-11-22T08:39:17Z)
• Mutual Information Alleviates Hallucinations in Abstractive Summarization [73.48162198041884]
  We find a simple criterion under which models are significantly more likely to assign more probability to hallucinated content during generation: high model uncertainty. This finding offers a potential explanation for hallucinations: models default to favoring text with high marginal probability, when uncertain about a continuation. We propose a decoding strategy that switches to optimizing for pointwise mutual information of the source and target token--rather than purely the probability of the target token--when the model exhibits uncertainty.
  arXiv  Detail & Related papers  (2022-10-24T13:30:54Z)
• Revisiting the Roles of "Text" in Text Games [102.22750109468652]
  This paper investigates the roles of text in the face of different reinforcement learning challenges. We propose a simple scheme to extract relevant contextual information into an approximate state hash. Such a lightweight plug-in achieves competitive performance with state-of-the-art text agents.
  arXiv  Detail & Related papers  (2022-10-15T21:52:39Z)
• Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization [7.851265919027389]
  We consider the problem of how to disentangle the gist-relevant and irrelevant information for long text understanding. Experiments on document classification, distantly supervised open-domain question answering (DS-QA) and non-parallel text style transfer show that our method can significantly improve the performance of the baseline models.
  arXiv  Detail & Related papers  (2021-10-10T09:21:24Z)
• On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator [0.30458514384586394]
  The drivers of compositionality emerge when two (or more) agents play a non-visual referential game. This paper investigates what extent the drivers of compositionality identified so far in the field apply in the ST-GS context. Using the ST-GS approach with small batch sizes and an overcomplete communication channel improves compositionality in the emerging languages.
  arXiv  Detail & Related papers  (2020-12-19T20:40:09Z)
• Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning [94.50608198582636]
  Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques. We take a novel perspective of IF game solving and re-formulate it as Multi-Passage Reading (MPRC) tasks.
  arXiv  Detail & Related papers  (2020-10-05T23:09:20Z)

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.