Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI Evaluation
Dimitris Gkoumas, Maria Liakata
Abstract
Scientific language models drive research innovation but require extensive fine-tuning on large datasets. This work enhances such models by improving their inference and evaluation capabilities with minimal or no additional training. Focusing on molecule caption generation, we explore post-training synergies between alignment fine-tuning and model merging in a cross-modal setup. We reveal intriguing insights into the behaviour and suitability of such methods while significantly surpassing state-of-the-art models. Moreover, we propose a novel atomic-level evaluation method leveraging off-the-shelf Natural Language Inference (NLI) models for use in the unseen chemical domain. Our experiments demonstrate that our evaluation operates at the right level of granularity, effectively handling multiple content units and subsentence reasoning, while widely adopted NLI methods consistently misalign with assessment criteria.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- QLoRA: Efficient Finetuning of Quantized LLMs cites Training language models to follow instructions with human feedback
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model cites Training language models to follow instructions with human feedback
Cited by top-tier papers1
Builds on25
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- QLoRA: Efficient Finetuning of Quantized LLMsTim Dettmers, Artidoro Pagnoni, Ari Holtzman, Luke ZettlemoyerNeurIPS 2023 · 5,863 citations
- Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timeMitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs et al.ICML 2022 · 1,464 citations
Related papers
- Improving Large Molecular Language Model via Relation-aware Multimodal CollaborationJinyoung Park, Minseong Bae, Jeehye Na, Hyunwoo J. KimAAAI 2026
- DeepMolTex: Deep Alignment of Molecular Graphs with Large Language Models via Mixture of Modality ExpertsMingliang Yan, Yanhua Yu, Ruochi Zhang, Zhiyuan Liu et al.ACM MM 2025
- Lost in Translation: Chemical Language Models and the Misunderstanding of Molecule StructuresVeronika Ganeeva, Andrey Sakhovskiy, Kuzma Khrabrov, Andrey V. Savchenko et al.EMNLP Findings 2024 · 3 citations
- MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and CorrectionYuyang Wu, Jinhui Ye, Shuhao Zhang, Lu Dai et al.EMNLP 2025 · 1 citation
- Unifying Molecular and Textual Representations via Multi-task Language ModellingDimitrios Christofidellis, Giorgio Giannone, Jannis Born, Ole Winther et al.ICML 2023 · 126 citations
