Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding
- URL: http://arxiv.org/abs/2405.02750v1
- Date: Sat, 4 May 2024 20:38:41 GMT
- Title: Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding
- Authors: Zheng Zhao, Emilio Monti, Jens Lehmann, Haytham Assem,
- Abstract summary: Large language models (LLMs) tend to inadequately integrate input context during text generation.
We introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples.
- Score: 9.2433070542025
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or contextually unfaithful content. LLMs utilize two primary knowledge sources: 1) prior (parametric) knowledge from pretraining, and 2) contextual (non-parametric) knowledge from input prompts. The study addresses the open question of how LLMs effectively balance these knowledge sources during the generation process, specifically in the context of open-domain question answering. To address this issue, we introduce a novel approach integrating contrastive decoding with adversarial irrelevant passages as negative samples to enhance robust context grounding during generation. Notably, our method operates at inference time without requiring further training. We conduct comprehensive experiments to demonstrate its applicability and effectiveness, providing empirical evidence showcasing its superiority over existing methodologies. Our code is publicly available at: https://github.com/amazon-science/ContextualUnderstanding-ContrastiveDecoding.
Related papers
- SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation [55.61004653386632]
Large Language Models (LLMs) often produce hallucinations, i.e., information that is unfaithful or not grounded in the input context.
This paper introduces a novel self-supervised method for generating a training set of unfaithful samples.
We then refine the model using a training process that encourages the generation of grounded outputs over unfaithful ones.
arXiv Detail & Related papers (2025-02-19T12:31:58Z) - Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation [81.18701211912779]
We introduce an Adaptive Multi-Aspect Retrieval-augmented over KGs (Amar) framework.
This method retrieves knowledge including entities, relations, and subgraphs, and converts each piece of retrieved text into prompt embeddings.
Our method has achieved state-of-the-art performance on two common datasets.
arXiv Detail & Related papers (2024-12-24T16:38:04Z) - Context-DPO: Aligning Language Models for Context-Faithfulness [80.62221491884353]
We propose the first alignment method specifically designed to enhance large language models' context-faithfulness.
By leveraging faithful and stubborn responses to questions with provided context from ConFiQA, our Context-DPO aligns LLMs through direct preference optimization.
Extensive experiments demonstrate that our Context-DPO significantly improves context-faithfulness, achieving 35% to 280% improvements on popular open-source models.
arXiv Detail & Related papers (2024-12-18T04:08:18Z) - Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering [9.86691461253151]
We introduce a novel method for attribution in contextual question answering, leveraging the hidden state representations of large language models (LLMs)
Our approach bypasses the need for extensive model retraining and retrieval model overhead, offering granular attributions and preserving the quality of generated answers.
We present Verifiability-granular, an attribution dataset which has token level annotations for LLM generations in the contextual question answering setup.
arXiv Detail & Related papers (2024-05-28T09:12:44Z) - Robust and Scalable Model Editing for Large Language Models [75.95623066605259]
We propose EREN (Edit models by REading Notes) to improve the scalability and robustness of LLM editing.
Unlike existing techniques, it can integrate knowledge from multiple edits, and correctly respond to syntactically similar but semantically unrelated inputs.
arXiv Detail & Related papers (2024-03-26T06:57:23Z) - DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain
Question Answering over Knowledge Base and Text [73.68051228972024]
Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge.
Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
arXiv Detail & Related papers (2023-10-31T04:37:57Z) - Context-faithful Prompting for Large Language Models [51.194410884263135]
Large language models (LLMs) encode parametric knowledge about world facts.
Their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks.
We assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention.
arXiv Detail & Related papers (2023-03-20T17:54:58Z)
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.