RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

Reward models are critical in techniques like Reinforcement Learning from Human Feedback (RLHF) and Inference Scaling Laws, where they guide language model alignment and select optimal responses. Despite their importance, existing reward model benchmarks often evaluate models by asking them to distinguish between responses generated by models of varying power. However, this approach fails to assess reward models on subtle but critical content changes and variations in style, resulting in a low correlation with policy model performance. To this end, we introduce RM-Bench, a novel benchmark designed to evaluate reward models based on their sensitivity to subtle content differences and resistance to style biases. Extensive experiments demonstrate that RM-Bench strongly correlates with policy model performance, making it a reliable reference for selecting reward models to align language models effectively. We evaluate nearly 40 reward models on RM-Bench. Our results reveal that even state-of-the-art models achieve an average performance of only 46.6%, which falls short of random-level accuracy (50%) when faced with style bias interference. These findings highlight the significant room for improvement in current reward models. Related code and data are available at https://github.com/THU-KEG/RM-Bench.

Pre-training Distillation for Large Language Models: A Design Space Exploration

Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model. Previous work applying KD in the field of large language models (LLMs) typically focused on the post-training phase, where the student LLM learns directly from instructions and corresponding responses generated by the teacher model. In this paper, we extend KD to the pre-training phase of LLMs, named pre-training distillation (PD). We first conduct a preliminary experiment using GLM-4-9B as the teacher LLM to distill a 1.9B parameter student LLM, validating the effectiveness of PD. Considering the key impact factors of distillation, we systematically explore the design space of pre-training distillation across four aspects: logits processing, loss selection, scaling law, and offline or online logits. We conduct extensive experiments to explore the design space of pre-training distillation and find better configurations and interesting conclusions, such as larger student LLMs generally benefiting more from pre-training distillation, while a larger teacher LLM does not necessarily guarantee better results. We hope our exploration of the design space will inform future practices in pre-training distillation.

Comparison of Autoencoder Encodings for ECG Representation in Downstream Prediction Tasks

The electrocardiogram (ECG) is an inexpensive and widely available tool for cardiovascular assessment. Despite its standardized format and small file size, the high complexity and inter-individual variability of ECG signals (typically a 60,000-size vector) make it challenging to use in deep learning models, especially when only small datasets are available. This study addresses these challenges by exploring feature generation methods from representative beat ECGs, focusing on Principal Component Analysis (PCA) and Autoencoders to reduce data complexity. We introduce three novel Variational Autoencoder (VAE) variants: Stochastic Autoencoder (SAE), Annealed beta-VAE (Abeta-VAE), and cyclical beta-VAE (Cbeta-VAE), and compare their effectiveness in maintaining signal fidelity and enhancing downstream prediction tasks. The Abeta-VAE achieved superior signal reconstruction, reducing the mean absolute error (MAE) to 15.7 plus-minus 3.2 microvolts, which is at the level of signal noise. Moreover, the SAE encodings, when combined with ECG summary features, improved the prediction of reduced Left Ventricular Ejection Fraction (LVEF), achieving an area under the receiver operating characteristic curve (AUROC) of 0.901. This performance nearly matches the 0.910 AUROC of state-of-the-art CNN models but requires significantly less data and computational resources. Our findings demonstrate that these VAE encodings are not only effective in simplifying ECG data but also provide a practical solution for applying deep learning in contexts with limited-scale labeled training data.

Meta-Learning on Augmented Gene Expression Profiles for Enhanced Lung Cancer Detection

Gene expression profiles obtained through DNA microarray have proven successful in providing critical information for cancer detection classifiers. However, the limited number of samples in these datasets poses a challenge to employ complex methodologies such as deep neural networks for sophisticated analysis. To address this "small data" dilemma, Meta-Learning has been introduced as a solution to enhance the optimization of machine learning models by utilizing similar datasets, thereby facilitating a quicker adaptation to target datasets without the requirement of sufficient samples. In this study, we present a meta-learning-based approach for predicting lung cancer from gene expression profiles. We apply this framework to well-established deep learning methodologies and employ four distinct datasets for the meta-learning tasks, where one as the target dataset and the rest as source datasets. Our approach is evaluated against both traditional and deep learning methodologies, and the results show the superior performance of meta-learning on augmented source data compared to the baselines trained on single datasets. Moreover, we conduct the comparative analysis between meta-learning and transfer learning methodologies to highlight the efficiency of the proposed approach in addressing the challenges associated with limited sample sizes. Finally, we incorporate the explainability study to illustrate the distinctiveness of decisions made by meta-learning.

Contrastive Learning on Medical Intents for Sequential Prescription Recommendation

Recent advancements in sequential modeling applied to Electronic Health Records (EHR) have greatly influenced prescription recommender systems. While the recent literature on drug recommendation has shown promising performance, the study of discovering a diversity of coexisting temporal relationships at the level of medical codes over consecutive visits remains less explored. The goal of this study can be motivated from two perspectives. First, there is a need to develop a sophisticated sequential model capable of disentangling the complex relationships across sequential visits. Second, it is crucial to establish multiple and diverse health profiles for the same patient to ensure a comprehensive consideration of different medical intents in drug recommendation. To achieve this goal, we introduce Attentive Recommendation with Contrasted Intents (ARCI), a multi-level transformer-based method designed to capture the different but coexisting temporal paths across a shared sequence of visits. Specifically, we propose a novel intent-aware method with contrastive learning, that links specialized medical intents of the patients to the transformer heads for extracting distinct temporal paths associated with different health profiles. We conducted experiments on two real-world datasets for the prescription recommendation task using both ranking and classification metrics. Our results demonstrate that ARCI has outperformed the state-of-the-art prescription recommendation methods and is capable of providing interpretable insights for healthcare practitioners.

LLMAEL: Large Language Models are Good Context Augmenters for Entity Linking

Entity Linking (EL) models are well-trained at mapping mentions to their corresponding entities according to a given context. However, EL models struggle to disambiguate long-tail entities due to their limited training data. Meanwhile, large language models (LLMs) are more robust at interpreting uncommon mentions. Yet, due to a lack of specialized training, LLMs suffer at generating correct entity IDs. Furthermore, training an LLM to perform EL is cost-intensive. Building upon these insights, we introduce LLM-Augmented Entity Linking LLMAEL, a plug-and-play approach to enhance entity linking through LLM data augmentation. We leverage LLMs as knowledgeable context augmenters, generating mention-centered descriptions as additional input, while preserving traditional EL models for task specific processing. Experiments on 6 standard datasets show that the vanilla LLMAEL outperforms baseline EL models in most cases, while the fine-tuned LLMAEL set the new state-of-the-art results across all 6 benchmarks.

Aligning Teacher with Student Preferences for Tailored Training Data Generation

Large Language Models (LLMs) have shown significant promise as copilots in various tasks. Local deployment of LLMs on edge devices is necessary when handling privacy-sensitive data or latency-sensitive tasks. The computational constraints of such devices make direct deployment of powerful large-scale LLMs impractical, necessitating the Knowledge Distillation from large-scale models to lightweight models. Lots of work has been done to elicit diversity and quality training examples from LLMs, but little attention has been paid to aligning teacher instructional content based on student preferences, akin to "responsive teaching" in pedagogy. Thus, we propose ARTE, dubbed Aligning TeacheR with StudenT PreferencEs, a framework that aligns the teacher model with student preferences to generate tailored training examples for Knowledge Distillation. Specifically, we elicit draft questions and rationales from the teacher model, then collect student preferences on these questions and rationales using students' performance with in-context learning as a proxy, and finally align the teacher model with student preferences. In the end, we repeat the first step with the aligned teacher model to elicit tailored training examples for the student model on the target task. Extensive experiments on academic benchmarks demonstrate the superiority of ARTE over existing instruction-tuning datasets distilled from powerful LLMs. Moreover, we thoroughly investigate the generalization of ARTE, including the generalization of fine-tuned student models in reasoning ability and the generalization of aligned teacher models to generate tailored training data across tasks and students. In summary, our contributions lie in proposing a novel framework for tailored training example generation, demonstrating its efficacy in experiments, and investigating the generalization of both student & aligned teacher models in ARTE.

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

This paper introduces Self-aware Knowledge Retrieval (SeaKR), a novel adaptive RAG model that extracts self-aware uncertainty of LLMs from their internal states. SeaKR activates retrieval when the LLMs present high self-aware uncertainty for generation. To effectively integrate retrieved knowledge snippets, SeaKR re-ranks them based on LLM's self-aware uncertainty to preserve the snippet that reduces their uncertainty to the utmost. To facilitate solving complex tasks that require multiple retrievals, SeaKR utilizes their self-aware uncertainty to choose among different reasoning strategies. Our experiments on both complex and simple Question Answering datasets show that SeaKR outperforms existing adaptive RAG methods. We release our code at https://github.com/THU-KEG/SeaKR.

Finding Safety Neurons in Large Language Models

Large language models (LLMs) excel in various capabilities but also pose safety risks such as generating harmful content and misinformation, even after safety alignment. In this paper, we explore the inner mechanisms of safety alignment from the perspective of mechanistic interpretability, focusing on identifying and analyzing safety neurons within LLMs that are responsible for safety behaviors. We propose generation-time activation contrasting to locate these neurons and dynamic activation patching to evaluate their causal effects. Experiments on multiple recent LLMs show that: (1) Safety neurons are sparse and effective. We can restore $90$% safety performance with intervention only on about $5$% of all the neurons. (2) Safety neurons encode transferrable mechanisms. They exhibit consistent effectiveness on different red-teaming datasets. The finding of safety neurons also interprets "alignment tax". We observe that the identified key neurons for safety and helpfulness significantly overlap, but they require different activation patterns of the shared neurons. Furthermore, we demonstrate an application of safety neurons in detecting unsafe outputs before generation. Our findings may promote further research on understanding LLM alignment. The source codes will be publicly released to facilitate future research.

DICE: Detecting In-distribution Contamination in LLM's Fine-tuning Phase for Math Reasoning

The advancement of large language models (LLMs) relies on evaluation using public benchmarks, but data contamination can lead to overestimated performance. Previous researches focus on detecting contamination by determining whether the model has seen the exact same data during training. In this work, we argue that even training on data similar to benchmark data inflates performance on in-distribution tasks without improving overall capacity, which we called In-distribution contamination. To effectively detect in-distribution contamination, we propose DICE, a novel method that leverages the internal states of LLMs to locate-then-detect the contamination. DICE first identifies the most sensitive layer to contamination, then trains a classifier based on the internal states of that layer. Experiments reveal DICE's high accuracy in detecting in-distribution contamination across various LLMs and math reasoning datasets. We also show the generalization capability of the trained DICE detector, which is able to detect contamination across multiple benchmarks with similar distributions. Additionally, we find that the DICE detection scores are positively correlated with the performance of ten LLMs fine-tuned by either us or other organizations on four math reasoning datasets (with $R^2$ values between 0.6 and 0.75). This indicates that the in-distribution contamination problem potentially lead to an overestimation of the true capabilities of many existing models. The code and data are available at https://github.com/THU-KEG/DICE.