Fine-tuning large language models requires minimal data, making them efficient.
problem Achieving state-of-the-art performance with large language models.
method Using BERT as an example, fine-tuning only the most critical layers of the pre-trained model.
result Fine-tuned models are close in parameter space to the pre-trained model, with many good solutions found in sparsified versions.
Fine-tuning LLMs improves capability but harms safety, study finds.
problem Balancing capability and safety in LLM fine-tuning.
method Theoretical framework and numerical experiments for two safety-aware fine-tuning strategies.
result Characterization of fundamental limits of safety-capability trade-off in LLM fine-tuning.
POUF fine-tunes large models without labeled data.
problem Lack of labeled data for fine-tuning large pre-trained models.
method Prompt-oriented unsupervised fine-tuning.
result Consistent improvements across various tasks.
L3Ms fine-tune LLMs with constraints for tailored applications.
problem Inadequate alignment of LLMs for diverse applications.
method Formulate SFT and alignment as constrained optimization, using logarithmic barriers.
result Versatile and effective in achieving tailored alignments for various applications.
DPZero fine-tunes large models privately without backpropagation.
problem Memory and privacy challenges in fine-tuning large language models.
method DPZero uses zeroth-order methods for private fine-tuning, avoiding backpropagation.
result DPZero achieves private fine-tuning of RoBERTa and OPT on various tasks.
FisherSFT selects informative examples to fine-tune LLMs efficiently.
problem Adapting large language models to new domains efficiently.
method Selects examples maximizing information gain using Hessian of log-likelihood.
result Empirically demonstrates improved performance with reduced computational cost.
UBM transfers bias mitigation from upstream to downstream tasks efficiently.
problem Bias in fine-tuned language models across various tasks.
method Apply bias mitigation to an upstream model, then fine-tune a downstream model on this mitigated model.
result UBM effects transfer to new downstream tasks, creating less biased models.
Paper fine-tunes LLMs for financial tasks using data fusion.
problem Improving LLMs for financial analysis tasks.
method Fine-tuned Llama3-8B and Mistral-7B using PEFT and LoRA, combined datasets for data fusion.
result Enhanced model performance across financial tasks.
Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective transfer learning method that can be applied to any task in NLP, and introduce tech…
AFTER technique improves NLP models by preventing overfitting to task-specific domains.
problem Standard fine-tuning degrades pretraining domain representations.
method Complements task-specific loss with adversarial objective.
result AFTER leads to improved performance on various NLP tasks.
Fine-tuning improves information conveyance in language models by reorganizing uncertainty into more informative sequences.
problem Uncertainty reduction in large language models through fine-tuning is not fully understood, especially regarding output length.
method Proposed Canopy Entropy (CE⋆) to measure uncertainty in both output length and sequence, capturing total Shannon entropy. result Fine-tuned models exhibit stronger positive correlation between entropy rate and semantic diversity, indicating more informative and semantically meaningful generations.
New algorithms improve privacy and utility of large language models.
problem Privacy-preserving fine-tuning of large language models.
method Meta-framework for differentially private fine-tuning, inspired by recent success in fine-tuning.
result Private fine-tuned models achieve utility close to non-private models, with improved privacy and efficiency.
Theoretical framework explains why few epochs are enough for LLM fine-tuning.
problem Understanding why few epochs are sufficient for LLM fine-tuning.
method Combining early stopping theory with attention-based Neural Tangent Kernel (NTK) for LLMs.
result Formalizes convergence rate of attention-based fine-tuning with respect to sample size.
Universal Language Model for Fine-tuning [arXiv:1801.06146] (ULMFiT) is one of the first NLP methods for efficient inductive transfer learning. Unsupervised pretraining results in improvements on many NLP tasks for English. In this paper, we describe a new method that uses subword tokenization to adapt ULMFiT to langua…
SymNoise improves language model fine-tuning by 6.7% over NEFTune, using symmetric noise.
problem Improving performance of language models through noise-based fine-tuning.
method Introducing SymNoise, a new fine-tuning method using symmetric noise in embeddings.
result SymNoise increases model performance by 69.04% on AlpacaEval compared to NEFTune's 64.69%.
Fine-tunes language models with captions for differential equation solving.
problem Overreliance on function data in operator learning.
method Integrates human knowledge through captions and fine-tunes language models.
result Significantly enhanced performance and reduced function data requirements.
The paper addresses poor calibration in fine-tuned LLMs after preference alignment.
problem Poor calibration in fine-tuned Large Language Models (LLMs) after preference alignment.
method Proposes a calibration-aware fine-tuning approach to restore calibration without compromising model performance.
result Demonstrates the effectiveness of the proposed methods through extensive experiments.
New method improves language model fine-tuning without forgetting.
problem Fine-tuning language models to match specific distributions without forgetting.
method Combines Distribution Matching and Reinforcement Learning techniques.
result Adding a baseline improves constraint satisfaction, stability, and efficiency.
The paper analyzes how forgetting in LLMs is linked to simple task-upstream example associations.
problem Forgetting of upstream knowledge in fine-tuned LLMs.
method Empirical analysis of forgotten examples in N upstream examples after M new tasks, using low-rank matrix approximation. result Forgetting can be predicted efficiently using matrix completion over empirical associations.
Generative Adversarial Networks (GANs) enjoy great success at image generation, but have proven difficult to train in the domain of natural language. Challenges with gradient estimation, optimization instability, and mode collapse have lead practitioners to resort to maximum likelihood pre-training, followed by small a…
LoRA-One uses one-step full gradient to align adapters for efficient large model fine-tuning.
problem Fine-tuning large language models efficiently and accurately.
method Properly initializing LoRA adapters using the one-step full gradient and incorporating preconditioners.
result LoRA-One achieves significant empirical improvements over existing methods.
JEPA fails to improve language model performance when fine-tuning.
problem Improving language model performance through latent representation learning.
method Testing various training-time auxiliaries on natural-language-to-regex generation.
result No auxiliary improves cross-entropy gradient cosine with decoder visibility.
In2Core selects a coreset for efficient LLM fine-tuning with reduced data.
problem Costly fine-tuning of large language models due to extensive parameters and data requirements.
method Analyzes model gradients to estimate training sample influence, optimizing for efficiency.
result Achieves similar performance with 50% of training data using In2Core.
Two methods for model adaptation compared; fine-tuning outperforms Best-of-N in realizable settings.
problem Comparing methods for adapting large language models to new tasks.
method Supervised fine-tuning vs. Best-of-N approach.
result Supervised fine-tuning outperforms Best-of-N in realizable settings.
SPIN converts weak LLMs to strong ones using self-play.
problem Growing strong LLMs without human-annotated data.
method Self-play fine-tuning (SPIN) starting from a supervised fine-tuned model.
result SPIN significantly improves LLM performance across benchmarks.
BLoB fine-tunes LLMs with Bayesian methods to improve uncertainty estimation.
problem Overconfidence in LLMs during inference for domain-specific tasks.
method Continuous Bayesian low-rank adaptation during fine-tuning.
result BLoB improves generalization and uncertainty estimation in LLMs.
This paper shows RL with KL penalties is equivalent to Bayesian inference for fine-tuning LMs.
problem Fine-tuning large language models to avoid undesirable features.
method Analyzed KL-regularized RL and showed it's equivalent to variational inference.
result KL-regularized RL avoids distribution collapse and is more insightful as Bayesian inference.
Recent Transformer-based contextual word representations, including BERT and XLNet, have shown state-of-the-art performance in multiple disciplines within NLP. Fine-tuning the trained contextual models on task-specific datasets has been the key to achieving superior performance downstream. While fine-tuning these pre-t…
Transformer models can solve complex math problems with less data.
problem Solving complex symbolic mathematics problems with limited data.
method Pretrain transformer models on language translation tasks and fine-tune for symbolic math.
result Pretrained transformer models achieve comparable accuracy to state-of-the-art models with less data.
In this work, we focus on fine-tuning an OpenAI GPT-2 pre-trained model for generating patent claims. GPT-2 has demonstrated impressive efficacy of pre-trained language models on various tasks, particularly coherent text generation. Patent claim language itself has rarely been explored in the past and poses a unique ch…
This paper fine-tunes LLMs for stock return prediction using financial news.
problem Improving stock return forecasting accuracy using LLMs.
method Fine-tuning LLMs with text and forecasting modules, comparing encoder-only and decoder-only models, and integrating token-level representations.
result LLMs' aggregated token-level embeddings enhance return predictions for long-only and long-short portfolios.
Robust CLIP improves vision models' resistance to attacks.
problem Vulnerability of vision models to adversarial attacks.
method Unsupervised adversarial fine-tuning of CLIP.
result Robust CLIP prevents stealth attacks on vision models.
New method quantifies uncertainty in fine-tuned LLMs using LoRA ensembles.
problem Uncertainty in fine-tuned LLMs and how to trust their predictions.
method Posterior approximations using low-rank adaptation ensembles.
result Unexpected retention of acquired knowledge during fine-tuning in overfitting regime.
New method fine-tunes discrete diffusion models for RLHF tasks.
problem Fine-tuning discrete diffusion models with policy gradient methods is challenging.
method Proposed SEPO algorithm for efficient fine-tuning over non-differentiable rewards.
result Numerical experiments show scalability and efficiency of SEPO.
Paper introduces NumLLM for better financial text understanding with numeric variables.
problem Poor performance of existing financial large language models in numeric financial text.
method Constructed financial corpus, fine-tuned with LoRA modules, merged into foundation model.
result NumLLM achieves best performance on financial question-answering benchmark, especially with numeric questions.
New approach uses inverse reinforcement learning to improve language model training.
problem Training large language models using imitation learning methods.
method Developed a new method of inverse reinforcement learning to optimize sequences directly.
result IRL-based fine-tuning leads to better performance and diversity in language generation.
The study examines label smoothing to improve confidence calibration in fine-tuned LLMs.
problem Improving confidence calibration in fine-tuned large language models (LLMs) after instruction tuning.
method Examine various open-sourced LLMs, label smoothing, and custom kernel design.
result Label smoothing is effective in maintaining confidence calibration but faces challenges in large vocabulary LLMs.
The ever-growing volume of data of user-generated content on social media provides a nearly unlimited corpus of unlabeled data even in languages where resources are scarce. In this paper, we demonstrate that state-of-the-art results on two Thai social text categorization tasks can be realized by pretraining a language …
GeLoRA optimizes LoRA fine-tuning by dynamically adjusting ranks based on intrinsic dimensionality.
problem Efficient fine-tuning of large language models with limited computational resources.
method GeLoRA computes intrinsic dimensionality to adaptively select LoRA ranks, balancing expressivity and efficiency.
result GeLoRA consistently outperforms recent baselines within the same parameter budget on multiple tasks.
Transformer models improve arithmetic accuracy with number decomposition.
problem Transformer models struggle with arithmetic operations without decomposition.
method Fine-tuning models with a pipeline that decomposes numbers into units, tens, etc.
result Accuracy increased by 63% in five-digit addition tasks.
Fine-tunes LLMs to correct bias in predictions.
problem LLMs exhibit bias in predictions from data.
method Supervised fine-tuning with Low-Rank Adaptation (LoRA).
result Fine-tuning corrects bias in both controlled and real-world settings.
LLM4Causal democratizes causal reasoning via fine-tuned LLMs.
problem Limited capability of LLMs in causal inference and interpretation.
method Fine-tuning an open-source LLM for causal tasks, proposing datasets for instruction tuning.
result LLM4Causal delivers end-to-end solutions for causal problems and interprets results easily.
DatedGPT prevents lookahead bias in financial forecasting models.
problem Lookahead bias in large language models trained on internet-scale data.
method Time-aware pretraining with annual data cutoffs and instruction fine-tuning.
result Models' knowledge is effectively bounded by their data cutoff year, improving forecasting validity.
Optimizes molecular generation for chemist preferences.
problem Models lack inherent preferences for chemist-desired structures.
method Fine-tuning with Direct Preference Optimization.
result Approach is simple, efficient, and highly effective.
BEMA reduces bias in EMA, leading to faster convergence and better performance.
problem Stochasticity in language model fine-tuning destabilizes training.
method Bias-Corrected Exponential Moving Average (BEMA) augmentation of EMA.
result BEMA leads to significantly improved convergence rates and final performance.
This study evaluates zero-shot LLMs in finance, finding ChatGPT performs well but fine-tuned models are better.
problem Evaluating zero-shot LLMs in financial tasks.
method Comparison of ChatGPT and fine-tuned models on annotated data.
result Fine-tuned models generally outperform zero-shot LLMs.
New approach uses compressible dynamics to train deep models efficiently.
problem Efficient training of deep overparameterized models with low-rank structures.
method Leveraging low-dimensional structures and compressible dynamics within model parameters.
result Improved training efficiency and reduced overfitting in language models.
Pre-training on different modalities improves Transformer performance in offline reinforcement learning.
problem Improving Transformer-based models for offline reinforcement learning tasks.
method Empirical investigation of pre-training on language and vision data, analysis of internal representations, and fine-tuning with no context.
result Pre-trained Transformers with language data can utilize context-like information to solve reinforcement learning tasks efficiently.