The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation

• URL: http://arxiv.org/abs/2508.14718v1
• Date: Wed, 20 Aug 2025 13:53:13 GMT
• Title: The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation
• Authors: Shubham Pundhir, Ganesh Bagler,
• Abstract summary: We present a comprehensive study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB.<n>Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers.
• Score: 2.497854684676663
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We established a rigorous benchmark for text-based recipe generation, a fundamental task in natural language generation. We present a comprehensive comparative study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB. Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers. This approach addresses a critical limitation of generic tokenizers by preserving essential recipe structures and precise numerical quantities, thereby enhancing domain specificity. Performance is evaluated using a comprehensive suite of seven automatic metrics spanning fluency (BLEU-4, METEOR), coherence (ROUGE-L), semantic relevance (BERTScore), and diversity. Our experiments show that the large transformer-based approach yields a >20% relative improvement in BERTScore (F1) (0.92 vs 0.72) over the best recurrent baseline, while reducing perplexity by 69.8%. We conclude with a discussion of remaining challenges, particularly regarding factual accuracy, and outline how this foundational study paves the way for integrating real-world constraints and multi-modal inputs in advanced recipe generation research.

Related papers

• T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning [31.85615810584119]
  We introduce Structure of Thought (SoT), a prompting technique that guides models to construct intermediate text structures.<n>Building upon this insight, we present T2S-Bench, the first benchmark designed to evaluate and improve text-to-structure capabilities of models.
  arXiv  Detail & Related papers  (2026-03-04T07:05:09Z)
• AI Generated Text Detection [0.0]
  This paper presents an evaluation of AI text detection methods, including both traditional machine learning models and transformer-based architectures.<n>We utilize two datasets, HC3 and DAIGT v2, to build a unified benchmark and apply a topic-based data split to prevent information leakage.<n>Results indicate that contextual modeling is significantly superior to lexical features and highlight the importance of mitigating topic memorization.
  arXiv  Detail & Related papers  (2026-01-07T11:18:10Z)
• Structured Reasoning with Tree-of-Thoughts for Bengali Math Word Problems [0.0]
  Chain-of-Thought (CoT) prompting has shown promise, but its linear structure often propagates errors.<n>We present the a systematic study of Tree-of-Thought (ToT) reasoning for Bengali MWPs using the SOMADHAN dataset.
  arXiv  Detail & Related papers  (2025-12-05T10:07:08Z)
• A Reproducible Framework for Neural Topic Modeling in Focus Group Analysis [0.0]
  We present a systematic framework for applying BERTopic to focus group transcripts using data from ten focus groups in Tunisia.<n> bootstrap stability analysis, performance metrics, and comparison with LDA baseline.<n>Findings demonstrate that transformer-based topic modeling can extract interpretable themes from small focus group transcript corpora.
  arXiv  Detail & Related papers  (2025-11-24T07:30:15Z)
• ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge [53.18163869901266]
  ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in Environmental, Social and Governance (ESG)<n> ESGenius comprises two key components: ESGenius-QA and ESGenius-Corpus.
  arXiv  Detail & Related papers  (2025-06-02T13:19:09Z)
• Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning [77.120955854093]
  We show that data diversity can be a strong predictor of generalization in language models.<n>We introduce G-Vendi, a metric that quantifies diversity via the entropy of model-induced gradients.<n>We present Prismatic Synthesis, a framework for generating diverse synthetic data.
  arXiv  Detail & Related papers  (2025-05-26T16:05:10Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models [6.349503549199403]
  This study presents a general evaluation framework using four key metrics: Human-reasoning Agreement (HA), Robustness, Consistency, and Contrastivity.<n>We assess the effectiveness of six explainability techniques from five different XAI categories.<n>Our findings show that the model simplification-based XAI method (LIME) consistently outperforms across multiple metrics and models.
  arXiv  Detail & Related papers  (2025-01-26T03:08:34Z)
• LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts [0.8495482945981923]
  This paper presents a system developed for Task 1 of the COLING 2025 Workshop on Detecting AI-Generated Content.<n>Our approach utilizes an ensemble of models, with weights assigned according to each model's inverse perplexity, to enhance classification accuracy.<n>Our results demonstrate the effectiveness of inverse perplexity weighting in improving the robustness of machine-generated text detection across both monolingual and multilingual settings.
  arXiv  Detail & Related papers  (2025-01-21T06:32:32Z)
• Building Math Agents with Multi-Turn Iterative Preference Learning [56.71330214021884]
  This paper studies the complementary direct preference learning approach to further improve model performance.<n>Existing direct preference learning algorithms are originally designed for the single-turn chat task.<n>We introduce a multi-turn direct preference learning framework, tailored for this context.
  arXiv  Detail & Related papers  (2024-09-04T02:41:04Z)
• MetaKP: On-Demand Keyphrase Generation [52.48698290354449]
  We introduce on-demand keyphrase generation, a novel paradigm that requires keyphrases that conform to specific high-level goals or intents. We present MetaKP, a large-scale benchmark comprising four datasets, 7500 documents, and 3760 goals across news and biomedical domains with human-annotated keyphrases. We demonstrate the potential of our method to serve as a general NLP infrastructure, exemplified by its application in epidemic event detection from social media.
  arXiv  Detail & Related papers  (2024-06-28T19:02:59Z)
• Markovian Transformers for Informative Language Modeling [1.172865818448696]
  Chain-of-Thought (CoT) reasoning often fails to faithfully reflect a language model's underlying decision process.<n>We introduce a Markovian language model framework that can be understood as a reasoning autoencoder.
  arXiv  Detail & Related papers  (2024-04-29T17:36:58Z)
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation [60.65820977963331]
  We introduce a novel evaluation paradigm for Large Language Models (LLMs) This paradigm shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-12-28T15:49:43Z)
• Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents [9.191944519634111]
  The Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG across various cut numbers and in overall success rate. Our solution involves the use of Large Language Models (LLMs) for initial answers, answer grounding by BM25, passage quality filtering by logistic regression, and answer generation by LLMs again.
  arXiv  Detail & Related papers  (2023-11-16T02:37:58Z)
• DiversiGATE: A Comprehensive Framework for Reliable Large Language Models [2.616506436169964]
  We introduce DiversiGATE, a unified framework that consolidates diverse methodologies for LLM verification. We propose a novel SelfLearner' model that conforms to the DiversiGATE framework and refines its performance over time. Our results demonstrate that our approach outperforms traditional LLMs, achieving a considerable 54.8% -> 61.8% improvement on the GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-06-22T22:29:40Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)

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.