Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations

• URL: http://arxiv.org/abs/2503.00134v3
• Date: Mon, 01 Sep 2025 04:16:57 GMT
• Title: Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations
• Abstract summary: We introduce a framework that enables Large Language Models to reason over individual-specific causal graphs constructed from longitudinal data.<n>In response to a query, the LLM traverses the graph to identify relevant causal pathways, rank them by estimated impact, simulate potential outcomes, and generate tailored responses.<n>We implement this framework in the context of nutrient-oriented dietary recommendations, where variability in metabolic responses demands personalized reasoning.
• Score: 0.5228101935101477
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) excel at general-purpose reasoning by leveraging broad commonsense knowledge, but they remain limited in tasks requiring personalized reasoning over multifactorial personal data. This limitation constrains their applicability in domains such as healthcare, where decisions must adapt to individual contexts. We introduce Personalized Causal Graph Reasoning, a framework that enables LLMs to reason over individual-specific causal graphs constructed from longitudinal data. Each graph encodes how user-specific factors influence targeted outcomes. In response to a query, the LLM traverses the graph to identify relevant causal pathways, rank them by estimated impact, simulate potential outcomes, and generate tailored responses. We implement this framework in the context of nutrient-oriented dietary recommendations, where variability in metabolic responses demands personalized reasoning. Using counterfactual evaluation, we assess the effectiveness of LLM-generated food suggestions for glucose control. Our method reduces postprandial glucose iAUC across three time windows compared to prior approaches. Additional LLM-as-a-judge evaluations further confirm improvements in personalization quality.

Related papers

• MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention [1.962656580942496]
  Postprandial hyperglycemia is a key risk factor for metabolic disorders.<n>Existing dietary guidance is often static, impractical, and insufficiently personalized.<n>We present MetaPlate, a context-aware framework that generates personalized meal recommendations.
  arXiv  Detail & Related papers  (2026-06-08T19:52:08Z)
• Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data [4.084164541001164]
  Wearable As Graph (WAG) organizes wearable metrics and user-specific signals into a personalized knowledge graph.<n>WAG retrieves a query-conditioned subgraph to support downstream generation.<n>We evaluate WAG on over 10,000 data-grounded queries from real-world wearable datasets.
  arXiv  Detail & Related papers  (2026-04-10T13:13:17Z)
• Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis [0.0]
  Epistemic blinding is a simple inference-time protocol that replaces entity identifiers with anonymous codes before prompting, then compares outputs against an unblinded control.<n>In oncology drug target prioritization across four cancer types, blinding changes 16% of top-20 predictions while preserving identical recovery of validated targets.<n>In S&P 500 equity screening, brand-recognition bias reshapes 30-40% of top-20 rankings across five random seeds.
  arXiv  Detail & Related papers  (2026-04-07T16:06:52Z)
• APRIL: Annotations for Policy evaluation with Reliable Inference from LLMs [1.4349869204948273]
  Off-policy evaluation (OPE) estimates the value of a contextual bandit policy prior to deployment.<n>Previous work has explored using expert-labeled counterfactual annotations to enhance dataset coverage.<n>We propose leveraging large language models (LLMs) to generate counterfactual annotations for OPE in medical domains.
  arXiv  Detail & Related papers  (2025-11-21T22:18:15Z)
• GraphOmni: A Comprehensive and Extendable Benchmark Framework for Large Language Models on Graph-theoretic Tasks [26.992997870540435]
  Graph Omni is a benchmark to evaluate the reasoning capabilities of LLMs on graph-theoretic tasks articulated in natural language.<n>We identify critical interactions among graph types, serialization formats, and prompting schemes, demonstrating their substantial impact on model performance.<n>We propose a reinforcement learning-inspired framework that adaptively selects the optimal factors influencing LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-04-17T09:01:16Z)
• Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering [66.5524727179286]
  NOVA is a framework designed to identify high-quality data that aligns well with the learned knowledge to reduce hallucinations.<n>It includes Internal Consistency Probing (ICP) and Semantic Equivalence Identification (SEI) to measure how familiar the LLM is with instruction data.<n>To ensure the quality of selected samples, we introduce an expert-aligned reward model, considering characteristics beyond just familiarity.
  arXiv  Detail & Related papers  (2025-02-11T08:05:56Z)
• Enhancing Patient-Centric Communication: Leveraging LLMs to Simulate Patient Perspectives [19.462374723301792]
  Large Language Models (LLMs) have demonstrated impressive capabilities in role-playing scenarios.<n>By mimicking human behavior, LLMs can anticipate responses based on concrete demographic or professional profiles.<n>We evaluate the effectiveness of LLMs in simulating individuals with diverse backgrounds and analyze the consistency of these simulated behaviors.
  arXiv  Detail & Related papers  (2025-01-12T22:49:32Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation [50.309987904297415]
  Major food recommendation platforms such as Yelp prioritize users' dietary preferences over the healthiness of their choices.<n>We develop a novel framework, Multi-Objective Personalized Interpretable Health-aware Food Recommendation System (MOPI-HFRS)<n>It provides food recommendations by jointly optimizing the three objectives: user preference, personalized healthiness and nutritional diversity, along with a large language model (LLM)-enhanced reasoning module.
  arXiv  Detail & Related papers  (2024-12-12T01:02:09Z)
• ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning [15.049688896236821]
  This paper presents ReasoningRec, a reasoning-based recommendation framework. ReasoningRec bridges the gap between recommendations and human-interpretable explanations. Empirical evaluations demonstrate that ReasoningRec surpasses state-of-the-art methods by up to 12.5% in recommendation prediction.
  arXiv  Detail & Related papers  (2024-10-30T16:37:04Z)
• Uncovering Factor Level Preferences to Improve Human-Model Alignment [58.50191593880829]
  We introduce PROFILE, a framework that uncovers and quantifies the influence of specific factors driving preferences. ProFILE's factor level analysis explains the 'why' behind human-model alignment and misalignment. We demonstrate how leveraging factor level insights, including addressing misaligned factors, can improve alignment with human preferences.
  arXiv  Detail & Related papers  (2024-10-09T15:02:34Z)
• Leveraging LLM Reasoning Enhances Personalized Recommender Systems [25.765908301183188]
  We show that the application of Large Language Models (LLMs) reasoning in recommendation systems (RecSys) presents a distinct challenge. Our study explores several aspects to better understand reasoning for RecSys and demonstrate how task quality improves.
  arXiv  Detail & Related papers  (2024-07-22T20:18:50Z)
• Evaluating Human Alignment and Model Faithfulness of LLM Rationale [66.75309523854476]
  We study how well large language models (LLMs) explain their generations through rationales. We show that prompting-based methods are less "faithful" than attribution-based explanations.
  arXiv  Detail & Related papers  (2024-06-28T20:06:30Z)
• Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments [41.25558612970942]
  We show that large language models (LLMs) exhibit preference biases and worrying sensitivity to prompt designs. Motivated by this phenomenon, we propose an automatic Zero-shot Evaluation-oriented Prompt Optimization framework, ZEPO.
  arXiv  Detail & Related papers  (2024-06-17T09:48:53Z)
• A Survey on Human Preference Learning for Large Language Models [81.41868485811625]
  The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning. This survey covers the sources and formats of preference feedback, the modeling and usage of preference signals, as well as the evaluation of the aligned LLMs.
  arXiv  Detail & Related papers  (2024-06-17T03:52:51Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) are used to automate decision-making tasks.<n>In this paper, we evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention.<n>We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types.<n>These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• LLMs-based Few-Shot Disease Predictions using EHR: A Novel Approach Combining Predictive Agent Reasoning and Critical Agent Instruction [38.11497959553319]
  We investigate the feasibility of applying Large Language Models to convert structured patient visit data into natural language narratives. We evaluate the zero-shot and few-shot performance of LLMs using various EHR-prediction-oriented prompting strategies. Our results demonstrate that with the proposed approach, LLMs can achieve decent few-shot performance compared to traditional supervised learning methods in EHR-based disease predictions.
  arXiv  Detail & Related papers  (2024-03-19T18:10:13Z)
• Causal Graph Discovery with Retrieval-Augmented Generation based Large Language Models [23.438388321411693]
  Causal graph recovery is traditionally done using statistical estimation-based methods or based on individual's knowledge about variables of interests. We propose a novel method that leverages large language models (LLMs) to deduce causal relationships in general causal graph recovery tasks.
  arXiv  Detail & Related papers  (2024-02-23T13:02:10Z)
• Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-based Retrofitting [51.7049140329611]
  This paper proposes Knowledge Graph-based Retrofitting (KGR) to mitigate factual hallucination during the reasoning process. Experiments show that KGR can significantly improve the performance of LLMs on factual QA benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T11:08:38Z)
• Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes [65.91730154730905]
  In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors. Here we tackle this by considering off-policy evaluation in a partially observed Markov decision process (POMDP) We extend the framework of proximal causal inference to our POMDP setting, providing a variety of settings where identification is made possible.
  arXiv  Detail & Related papers  (2021-10-28T17:46:14Z)

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.