The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring rubrics. Existing methods for LLM-as-a-judge use cross-entropy (CE) loss for fine-tuning, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning, which, however, does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), a method combining CoT reasoning with regression-aware training. TRACT consists of two stages: first, seed LLM is fine-tuned to generate CoTs, which serve as supervision for the second stage fine-tuning. The training objective of TRACT combines the CE loss for learning the CoT reasoning capabilities, and the regression-aware loss for the score prediction. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the importance of each component in TRACT.

Large language models (LLMs) have demonstrated strong results on a range of NLP tasks. Typically, outputs are obtained via autoregressive sampling from the LLM's underlying distribution. Building on prior work on Minimum Bayes Risk decoding, we show that this inference strategy can be suboptimal for a range of regression and scoring tasks, and associated evaluation metrics. As a remedy, we propose metric aware LLM inference: a decision theoretic approach optimizing for custom regression and scoring metrics at inference time. We report improvements over baselines on academic benchmarks and publicly available models.

The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns. Inspired by this, we explore a novel mechanism to improve model generalization via explicit memorization. Specifically, we propose the residual-memorization (ResMem) algorithm, a new method that augments an existing prediction model (e.g., a neural network) by fitting the model's residuals with a k-nearest neighbor based regressor. The final prediction is then the sum of the original model and the fitted residual regressor. By construction, ResMem can explicitly memorize the training labels, even when the base model has low capacity. We start by formulating a stylized linear regression problem and rigorously show that ResMem results in a more favorable test risk over a base linear neural network. Then, we empirically show that ResMem consistently improves the test set generalization of the original prediction model across standard vision and natural language processing benchmarks.

The concepts of bias and variance, obtained from decomposing the generalization error, are of fundamental importance in machine learning. Classical wisdom suggests that there is a trade-off between bias and variance: models of low capacity have high bias and low variance, while models of high capacity have low bias and high variance. This understanding served as an important guiding principle for developing generalizable machine learning models, suggesting that they should be neither too large nor too small [Bishop, 2006]. Recently, a line of research found that deep models defy this classical wisdom [Belkin et al., 2019]: their variance curves exhibit a unimodal shape that first increases with model size, then decreases beyond the point that the models can perfectly fit the training data [Neal et al., 2018, Yang et al., 2020]. While the unimodal variance curve explains why over-parameterized deep models generalize well, there is still a lack of understanding on why it occurs. This paper revisits the study of bias and variance to understand their behavior in deep models. We perform a per-sample measurement of bias and variance in popular deep classification models. Our study reveals a curious phenomenon, which is radically different from the classical tradeoff perspective on bias-variance, while is concordant with more recent works [Belkin et al., 2019, Hastie et al., 2022, Mei and Montanari, 2022].

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels. To carefully study this issue, Feldman proposed a metric to quantify the degree of memorisation of individual training examples, and empirically computed the corresponding memorisation profile of a ResNet on image classification bench-marks. While an exciting first glimpse into what real-world models memorise, this leaves open a fundamental question: do larger neural models memorise more? We present a comprehensive empirical analysis of this question on image classification benchmarks. We find that training examples exhibit an unexpectedly diverse set of memorisation trajectories across model sizes: most samples experience decreased memorisation under larger models, while the rest exhibit cap-shaped or increasing memorisation. We show that various proxies for the Feldman memorization score fail to capture these fundamental trends. Lastly, we find that knowledge distillation, an effective and popular model compression technique, tends to inhibit memorisation, while also improving generalisation. Specifically, memorisation is mostly inhibited on examples with increasing memorisation trajectories, thus pointing at how distillation improves generalisation.

Pretrained large language models (LLMs) are general purpose problem solvers applicable to a diverse set of tasks with prompts. They can be further improved towards a specific task by fine-tuning on a specialized dataset. However, fine-tuning usually makes the model narrowly specialized on this dataset with reduced general in-context learning performances, which is undesirable whenever the fine-tuned model needs to handle additional tasks where no fine-tuning data is available. In this work, we first demonstrate that fine-tuning on a single task indeed decreases LLMs' general in-context learning performance. We discover one important cause of such forgetting, format specialization, where the model overfits to the format of the fine-tuned task. We further show that format specialization happens at the very beginning of fine-tuning. To solve this problem, we propose Prompt Tuning with MOdel Tuning (ProMoT), a simple yet effective two-stage fine-tuning framework that reduces format specialization and improves generalization. ProMoT offloads task-specific format learning into additional and removable parameters by first doing prompt tuning and then fine-tuning the model itself with this soft prompt attached. With experiments on several fine-tuning tasks and 8 in-context evaluation tasks, we show that ProMoT achieves comparable performance on fine-tuned tasks to standard fine-tuning, but with much less loss of in-context learning performances across a board range of out-of-domain evaluation tasks. More importantly, ProMoT can even enhance generalization on in-context learning tasks that are semantically related to the fine-tuned task, e.g. ProMoT on En-Fr translation significantly improves performance on other language pairs, and ProMoT on NLI improves performance on summarization. Experiments also show that ProMoT can improve the generalization performance of multi-task training.

Graph neural networks (GNNs) have emerged as a powerful approach for solving many network mining tasks. However, learning on large graphs remains a challenge - many recently proposed scalable GNN approaches rely on an expensive message-passing procedure to propagate information through the graph. We present the PPRGo model which utilizes an efficient approximation of information diffusion in GNNs resulting in significant speed gains while maintaining state-of-the-art prediction performance. In addition to being faster, PPRGo is inherently scalable, and can be trivially parallelized for large datasets like those found in industry settings. We demonstrate that PPRGo outperforms baselines in both distributed and single-machine training environments on a number of commonly used academic graphs. To better analyze the scalability of large-scale graph learning methods, we introduce a novel benchmark graph with 12.4 million nodes, 173 million edges, and 2.8 million node features. We show that training PPRGo from scratch and predicting labels for all nodes in this graph takes under 2 minutes on a single machine, far outpacing other baselines on the same graph. We discuss the practical application of PPRGo to solve large-scale node classification problems at Google.

Time series modeling is an important problem with many applications in different domains. Here we consider discriminative learning from time series, where we seek to predict an output response variable based on time series input. We develop a method based on convolution kernels to model discriminative learning over streams of text. Our method outperforms competitive baselines in three synthetic and two real datasets, rumour frequency modeling and popularity prediction tasks.