# LM-Cocktail: Resilient Tuning of Language Models via Model Merging

arXiv: https://arxiv.org/abs/2311.13534 · HTML: https://mlsanity.com/paper/2311.13534/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 56 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch](https://mlsanity.com/paper/2311.03099/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [Dataless Knowledge Fusion by Merging Weights of Language Models](https://mlsanity.com/paper/2212.09849/) (2022)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)

## Built on by (most cited first, 30 of 44)

- [Retrieval-Augmented Generation for AI-Generated Content: A Survey](https://mlsanity.com/paper/2402.19473/) (2024)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [Revisiting Catastrophic Forgetting in Large Language Model Tuning](https://mlsanity.com/paper/2406.04836/) (2024)
- [WARP: On the Benefits of Weight Averaged Rewarded Policies](https://mlsanity.com/paper/2406.16768/) (2024)
- [Model Merging and Safety Alignment: One Bad Model Spoils the Bunch](https://mlsanity.com/paper/2406.14563/) (2024)
- [M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions](https://mlsanity.com/paper/2405.16420/) (2024)
- [KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model](https://mlsanity.com/paper/2506.20923/) (2025)
- [Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs](https://mlsanity.com/paper/2406.16797/) (2024)
- [KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking](https://mlsanity.com/paper/2404.02935/) (2024)
- [The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design](https://mlsanity.com/paper/2408.12503/) (2024)
- [MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge](https://mlsanity.com/paper/2412.17032/) (2024)
- [Fun-Audio-Chat Technical Report](https://mlsanity.com/paper/2512.20156/) (2025)
- [HFT: Half Fine-Tuning for Large Language Models](https://mlsanity.com/paper/2404.18466/) (2024)
- [Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning](https://mlsanity.com/paper/2410.10801/) (2024)
- [Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning](https://mlsanity.com/paper/2403.10056/) (2024)
- [Granite Embedding Models](https://mlsanity.com/paper/2502.20204/) (2025)
- [HumanLLM: Towards Personalized Understanding and Simulation of Human Nature](https://mlsanity.com/paper/2601.15793/) (2026)
- [LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion](https://mlsanity.com/paper/2602.00038/) (2026)
- [LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint](https://mlsanity.com/paper/2502.16770/) (2025)
- [Merge to Mix: Mixing Datasets via Model Merging](https://mlsanity.com/paper/2505.16066/) (2025)
- [Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs](https://mlsanity.com/paper/2503.07663/) (2025)
- [DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations](https://mlsanity.com/paper/2506.09349/) (2025)
- [HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging](https://mlsanity.com/paper/2507.17706/) (2025)
- [Temporal Information Retrieval via Time-Specifier Model Merging](https://mlsanity.com/paper/2507.06782/) (2025)
- [RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging](https://mlsanity.com/paper/2510.20479/) (2025)
- [A Systematic Study of In-the-Wild Model Merging for Large Language Models](https://mlsanity.com/paper/2511.21437/) (2025)
- [Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging](https://mlsanity.com/paper/2410.03743/) (2024)
- [Efficient Compositional Multi-tasking for On-device Large Language Models](https://mlsanity.com/paper/2507.16083/) (2025)
- [K-Merge: Online Continual Merging of Adapters for On-device Large Language Models](https://mlsanity.com/paper/2510.13537/) (2025)
- [Activated Parameter Locating via Causal Intervention for Model Merging](https://mlsanity.com/paper/2408.09485/) (2024)

## Abstract (arXiv)

The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this problem, we propose LM-Cocktail which enables the fine-tuned model to stay resilient in general perspectives. Our method is conducted in the form of model merging, where the fine-tuned language model is merged with the pre-trained base model or the peer models from other domains through weighted average. Despite simplicity, LM-Cocktail is surprisingly effective: the resulted model is able to achieve a strong empirical performance in the whole scope of general tasks while preserving a superior capacity in its targeted domain. We conduct comprehensive experiments with LLama and BGE model on popular benchmarks, including FLAN, MMLU, MTEB, whose results validate the efficacy of our proposed method. The code and checkpoints are available at https://github.com/FlagOpen/FlagEmbedding/tree/master/LM_Cocktail.