Graph Retrieval Augmented Trustworthiness Reasoning
- URL: http://arxiv.org/abs/2408.12333v2
- Date: Wed, 4 Sep 2024 12:00:25 GMT
- Title: Graph Retrieval Augmented Trustworthiness Reasoning
- Authors: Ying Zhu, Shengchang Li, Ziqian Kong, Peilan Xu,
- Abstract summary: We introduce the Graph Retrieval Augmented Reasoning (GRATR) framework to bolster trustworthiness reasoning in agents.
GRATR constructs a dynamic trustworthiness graph, updating it in real-time with evidential information.
Our results demonstrate GRATR surpasses the baseline methods by over 30% in winning rate, with superior reasoning performance.
- Score: 1.1660282484277826
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Trustworthiness reasoning is crucial in multiplayer games with incomplete information, enabling agents to identify potential allies and adversaries, thereby enhancing reasoning and decision-making processes. Traditional approaches relying on pre-trained models necessitate extensive domain-specific data and considerable reward feedback, with their lack of real-time adaptability hindering their effectiveness in dynamic environments. In this paper, we introduce the Graph Retrieval Augmented Reasoning (GRATR) framework, leveraging the Retrieval-Augmented Generation (RAG) technique to bolster trustworthiness reasoning in agents. GRATR constructs a dynamic trustworthiness graph, updating it in real-time with evidential information, and retrieves relevant trust data to augment the reasoning capabilities of Large Language Models (LLMs). We validate our approach through experiments on the multiplayer game "Werewolf," comparing GRATR against baseline LLM and LLM enhanced with Native RAG and Rerank RAG. Our results demonstrate that GRATR surpasses the baseline methods by over 30\% in winning rate, with superior reasoning performance. Moreover, GRATR effectively mitigates LLM hallucinations, such as identity and objective amnesia, and crucially, it renders the reasoning process more transparent and traceable through the use of the trustworthiness graph.
Related papers
- Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking [7.946359845249688]
Large Language Models (LLMs) have shown strong performance across fact-checking tasks.
This paper investigates whether generative agents can meaningfully contribute to fact-checking tasks traditionally reserved for human crowds.
Agent crowds outperform human crowds in truthfulness classification, exhibit higher internal consistency, and show reduced susceptibility to social and cognitive biases.
arXiv Detail & Related papers (2025-04-24T18:49:55Z) - Lie Detector: Unified Backdoor Detection via Cross-Examination Framework [68.45399098884364]
We propose a unified backdoor detection framework in the semi-honest setting.
Our method achieves superior detection performance, improving accuracy by 5.4%, 1.6%, and 11.9% over SoTA baselines.
Notably, it is the first to effectively detect backdoors in multimodal large language models.
arXiv Detail & Related papers (2025-03-21T06:12:06Z) - ClaimTrust: Propagation Trust Scoring for RAG Systems [7.7690689135107425]
ClaimTrust is a propagation-based trust scoring framework that dynamically evaluates the reliability of documents in a RAG system.
We preprocess and analyze 814 political news articles to extract 2,173 unique claims and classify 965 meaningful relationships.
ClaimTrust iteratively updates trust scores until convergence, effectively differentiating trustworthy articles from unreliable ones.
arXiv Detail & Related papers (2025-03-12T07:52:24Z) - Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation [9.844598565914055]
Large Language Models (LLMs) demonstrate strong reasoning abilities but face limitations such as hallucinations and outdated knowledge.
We introduce SubgraphRAG, extending the Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) framework that retrieves subgraphs.
Our approach innovatively integrates a lightweight multilayer perceptron with a parallel triple-scoring mechanism for efficient and flexible subgraph retrieval.
arXiv Detail & Related papers (2024-10-28T04:39:32Z) - Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness.
We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
arXiv Detail & Related papers (2024-10-21T17:00:06Z) - Criticality and Safety Margins for Reinforcement Learning [53.10194953873209]
We seek to define a criticality framework with both a quantifiable ground truth and a clear significance to users.
We introduce true criticality as the expected drop in reward when an agent deviates from its policy for n consecutive random actions.
We also introduce the concept of proxy criticality, a low-overhead metric that has a statistically monotonic relationship to true criticality.
arXiv Detail & Related papers (2024-09-26T21:00:45Z) - WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs [10.380692079063467]
We propose WeKnow-RAG, which integrates Web search and Knowledge Graphs into a "Retrieval-Augmented Generation (RAG)" system.
First, the accuracy and reliability of LLM responses are improved by combining the structured representation of Knowledge Graphs with the flexibility of dense vector retrieval.
Our approach effectively balances the efficiency and accuracy of information retrieval, thus improving the overall retrieval process.
arXiv Detail & Related papers (2024-08-14T15:19:16Z) - TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs [50.259001311894295]
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.
arXiv Detail & Related papers (2024-07-06T07:19:30Z) - InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales [14.655518998487237]
We propose InstructRAG, where LMs explicitly learn the denoising process through self-synthesized rationales.
InstructRAG requires no additional supervision, allows for easier verification of the predicted answers.
Experiments show InstructRAG consistently outperforms existing RAG methods in both training-free and trainable scenarios.
arXiv Detail & Related papers (2024-06-19T15:25:29Z) - Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.
We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.
We also use ARE to rigorously evaluate how the robustness changes as new components are added.
arXiv Detail & Related papers (2024-06-18T17:32:48Z) - Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation [47.42366169887162]
Credibility-aware Generation (CAG) aims to equip models with the ability to discern and process information based on its credibility.
Our model can effectively understand and utilize credibility for generation, significantly outperform other models with retrieval augmentation, and exhibit resilience against the disruption caused by noisy documents.
arXiv Detail & Related papers (2024-04-10T07:56:26Z) - InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling [66.3072381478251]
Reward hacking, also termed reward overoptimization, remains a critical challenge.
We propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective.
We show that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets.
arXiv Detail & Related papers (2024-02-14T17:49:07Z) - Minimizing Factual Inconsistency and Hallucination in Large Language
Models [0.16417409087671928]
Large Language Models (LLMs) are widely used in critical fields such as healthcare, education, and finance.
We propose a multi-stage framework that generates the rationale first, verifies and refines incorrect ones, and uses them as supporting references to generate the answer.
Our framework improves traditional Retrieval Augmented Generation (RAG) by enabling OpenAI GPT-3.5-turbo to be 14-25% more faithful and 16-22% more accurate on two datasets.
arXiv Detail & Related papers (2023-11-23T09:58:39Z) - Self-RAG: Learning to Retrieve, Generate, and Critique through
Self-Reflection [74.51523859064802]
We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG)
Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection.
It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
arXiv Detail & Related papers (2023-10-17T18:18:32Z) - Client-side Gradient Inversion Against Federated Learning from Poisoning [59.74484221875662]
Federated Learning (FL) enables distributed participants to train a global model without sharing data directly to a central server.
Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples.
We propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients.
arXiv Detail & Related papers (2023-09-14T03:48:27Z) - A Closer Look at Debiased Temporal Sentence Grounding in Videos:
Dataset, Metric, and Approach [53.727460222955266]
Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video.
Recent studies have found that current benchmark datasets may have obvious moment annotation biases.
We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
arXiv Detail & Related papers (2022-03-10T08:58:18Z) - Personalized multi-faceted trust modeling to determine trust links in
social media and its potential for misinformation management [61.88858330222619]
We present an approach for predicting trust links between peers in social media.
We propose a data-driven multi-faceted trust modeling which incorporates many distinct features for a comprehensive analysis.
Illustrated in a trust-aware item recommendation task, we evaluate the proposed framework in the context of a large Yelp dataset.
arXiv Detail & Related papers (2021-11-11T19:40:51Z) - Learning to Give Checkable Answers with Prover-Verifier Games [23.93694563816463]
We introduce Prover-Verifier Games (PVGs), a game-theoretic framework to encourage learning agents to solve decision problems in a verifiable manner.
We analyze variants of the framework, including simultaneous and sequential games, and narrow the space down to a subset of games which provably have the desired equilibria.
We develop instantiations of the PVG for two algorithmic tasks, and show that in practice, the verifier learns a robust decision rule that is able to receive useful and reliable information from an untrusted prover.
arXiv Detail & Related papers (2021-08-27T02:56:06Z) - BaFFLe: Backdoor detection via Feedback-based Federated Learning [3.6895394817068357]
We propose Backdoor detection via Feedback-based Federated Learning (BAFFLE)
We show that BAFFLE reliably detects state-of-the-art backdoor attacks with a detection accuracy of 100% and a false-positive rate below 5%.
arXiv Detail & Related papers (2020-11-04T07:44:51Z)
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.