Related papers: Distilled Self-Critique of LLMs with Synthetic Dat…

Imbalanced data are commonly present in real-world applications. While data synthesis can effectively mitigate data scarcity for rare classes, and LLMs have revolutionized text generation, the application of LLMs to the synthesis of…

In this paper, we will propose linear-matrix-inequality-based techniques for the design of sampled-data controllers that render the closed-loop system dissipative with respect to \textcolor{blue}{quadratic supply functions}, which includes…

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Dataset distillation is the task of synthesizing a small dataset such that a model trained on the synthetic set will match the test accuracy of the model trained on the full dataset. In this paper, we propose a new formulation that…

Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume…

The LLM-as-a-judge paradigm enables flexible, user-defined evaluation, but its effectiveness is often limited by the scarcity of diverse, representative data for refining criteria. We present a tool that integrates synthetic data generation…

With the rise of powerful closed-sourced LLMs (ChatGPT, GPT-4), there are increasing interests in distilling the capabilies of close-sourced LLMs to smaller open-sourced LLMs. Previous distillation methods usually prompt ChatGPT to generate…

Learning from noisy data has become essential for adapting deep learning models to real-world applications. Traditional methods often involve first evaluating the noise and then applying strategies such as discarding noisy samples,…

In many practical applications, large language models (LLMs) need to acquire new knowledge not present in their pre-training data. Efficiently leveraging this knowledge usually relies on supervised fine-tuning or retrieval-augmented…

Insider threats wield an outsized influence on organizations, disproportionate to their small numbers. This is due to the internal access insiders have to systems, information, and infrastructure. %One example of this influence is where…

The synthetic control method has become a widely popular tool to estimate causal effects with observational data. Despite this, inference for synthetic control methods remains challenging. Often, inferential results rely on linear factor…

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

Self-Consistency (SC) is an effective decoding strategy that improves the reasoning performance of Large Language Models (LLMs) by generating multiple chain-of-thought reasoning paths and selecting the final answer via majority voting.…

Lexical Semantic Change (LSC) provides insight into cultural and social dynamics. Yet, the validity of methods for measuring different kinds of LSC remains unestablished due to the absence of historical benchmark datasets. To address this…

Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to create a social media post "in a funny tone" with "no…

Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on…

This paper explores targeted distillation methods for sentiment analysis, aiming to build compact and practical models that preserve strong and generalizable sentiment analysis capabilities. To this end, we conceptually decouple the…

Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…

Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and…

Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under…