TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs

• URL: http://arxiv.org/abs/2407.04981v1
• Date: Sat, 6 Jul 2024 07:19:30 GMT
• Title: TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
• Authors: Cheng Wang, Xinyang Lu, See-Kiong Ng, Bryan Kian Hsiang Low,
• Abstract summary: We propose a novel TRansformer-based Attribution framework using Contrastive Embeddings called TRACE. We show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of large language models.
• Score: 50.259001311894295
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparency of LLM responses. Reliable source attribution is essential to adhering to stringent legal and regulatory standards, including those set forth by the General Data Protection Regulation. Despite the well-established methods in source attribution within the computer vision domain, the application of robust attribution frameworks to natural language processing remains underexplored. To bridge this gap, we propose a novel and versatile TRansformer-based Attribution framework using Contrastive Embeddings called TRACE that, in particular, exploits contrastive learning for source attribution. We perform an extensive empirical evaluation to demonstrate the performance and efficiency of TRACE in various settings and show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of LLMs.

Related papers

• Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach [33.463823493423554]
  Multimodal large language models (MLLMs) have shown promising capabilities but struggle under distribution shifts. We argue that establishing a formal framework that can characterize and quantify the risk of MLLMs is necessary to ensure the safe and reliable application of MLLMs in the real world.
  arXiv  Detail & Related papers  (2025-02-01T22:06:56Z)
• Aligning Large Language Models for Faithful Integrity Against Opposing Argument [71.33552795870544]
  Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. They can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. We propose a novel framework, named Alignment for Faithful Integrity with Confidence Estimation.
  arXiv  Detail & Related papers  (2025-01-02T16:38:21Z)
• Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion [28.724919973497943]
  Large language models (LLMs) and rule-based reasoning offer a powerful solution for improving the flexibility and reliability of Knowledge Base Completion. We propose a novel framework consisting of a Subgraph Extractor, an LLM Proposer, and a Rule Reasoner. Our approach offers several key benefits: the utilization of LLMs to enhance the richness and diversity of the proposed rules, and the integration with rule-based reasoning to improve reliability.
  arXiv  Detail & Related papers  (2025-01-02T13:14:28Z)
• CATER: Leveraging LLM to Pioneer a Multidimensional, Reference-Independent Paradigm in Translation Quality Evaluation [0.0]
  Comprehensive AI-assisted Translation Edit Ratio (CATER) is a novel framework for evaluating machine translation (MT) quality. Uses large language models (LLMs) via a carefully designed prompt-based protocol.
  arXiv  Detail & Related papers  (2024-12-15T17:45:34Z)
• Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal [21.342265570934995]
  Existing methods have largely overlooked the importance of refusal responses as a means of enhancing MLLMs reliability. We present the Information Boundary-aware Learning Framework (InBoL), a novel approach that empowers MLLMs to refuse to answer user queries when encountering insufficient information. This framework introduces a comprehensive data generation pipeline and tailored training strategies to improve the model's ability to deliver appropriate refusal responses.
  arXiv  Detail & Related papers  (2024-12-15T14:17:14Z)
• Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness [39.74642729786543]
  We argue that current factuality enhancement methods can significantly undermine context-faithfulness of large language models (LLMs) Experiments reveal that while these methods may yield inconsistent improvements in factual accuracy, they also cause a more severe decline in context-faithfulness.
  arXiv  Detail & Related papers  (2024-03-30T02:08:28Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)
• Source Attribution for Large Language Model-Generated Data [57.85840382230037]
  It is imperative to be able to perform source attribution by identifying the data provider who contributed to the generation of a synthetic text. We show that this problem can be tackled by watermarking. We propose a source attribution framework that satisfies these key properties due to our algorithmic designs.
  arXiv  Detail & Related papers  (2023-10-01T12:02:57Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Balancing Discriminability and Transferability for Source-Free Domain Adaptation [55.143687986324935]
  Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations. The requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting. We derive novel insights to show that a mixup between original and corresponding translated generic samples enhances the discriminability-transferability trade-off.
  arXiv  Detail & Related papers  (2022-06-16T09:06:22Z)

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.