Related papers: Learning to Reason in 13 Parameters
Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static parameter allocation remains suboptimal for inputs of varying complexity. We present…
Scaling laws are useful guides for derisking expensive training runs, as they predict performance of large models using cheaper, small-scale experiments. However, there remain gaps between current scaling studies and how language models are…
Fine-tuning is a key approach for adapting language models to specific downstream tasks, but updating all model parameters becomes impractical as model sizes increase. Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank…
Reasoning has long been viewed as an emergent property of large language models (LLMs). However, recent studies challenge this assumption, showing that small language models (SLMs) can also achieve competitive reasoning performance. This…
Large language models show promise for legal applications, but deploying frontier models raises concerns about cost, latency, and data privacy. We evaluate whether sub-10B parameter models can serve as practical alternatives by testing nine…
Recent advances in mathematical reasoning typically rely on massive scale, yet the question remains: can strong reasoning capabilities be induced in small language models ($\leq1.5\text{B}$) under extreme constraints? We investigate this by…
State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance. Our study focuses on Transformer-based LLMs,…
Pre-trained Large Language Models (LLMs) have revolutionized text processing, yet adapting Transformer-based neural networks to non-textual scientific modalities typically requires specialized architectures and extensive computational…
Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) that incorporate reflection, backtracking, and self-validation. However, the training techniques and data requirements to elicit…
As large language models (LLMs) have become increasingly compute and memory intensive, parameter-efficient fine-tuning (PEFT) methods are now a common strategy to fine-tune LLMs. A popular PEFT method is Low-Rank Adapters (LoRA), which adds…
Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource…
Despite their widespread use, large language models (LLMs) are known to hallucinate incorrect information and be poorly calibrated. This makes the uncertainty quantification of these models of critical importance, especially in high-stakes…
In this paper, we present Delta-LoRA, which is a novel parameter-efficient approach to fine-tune large language models (LLMs). In contrast to LoRA and other low-rank adaptation methods such as AdaLoRA, Delta-LoRA not only updates the…
We show that training a single $d$-dimensional steering vector per layer with reinforcement learning, while freezing all base weights, matches the accuracy of fully RL-tuned reasoning models on mathematical-reasoning tasks. On an 8…
Fine-tuning large language models (LLMs) with parameter-efficient techniques such as LoRA and QLoRA has enabled adaptation of foundation models on modest hardware. Yet the efficiency of such training on consumer-grade GPUs, especially under…
Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among Parameter-Efficient Fine-Tuning (PEFT) methods, Low-Rank Adaptation (LoRA) stands out by…
Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training…
Parameter-efficient fine-tuning (PEFT) methods face a tradeoff between adapter size and expressivity: ultra-low-parameter adapters are confined to fixed low-rank subspaces, capping performance even with extended training. We propose…
Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…
Low-Rank Adaptation (LoRA) is a popular method for parameter-efficient fine-tuning (PEFT) of generative models, valued for its simplicity and effectiveness. Despite recent enhancements, LoRA still suffers from a fundamental limitation:…