Related papers: Self-Improving Language Models with Bidirectional …

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compressed evidence features…

Decision trees are a crucial class of models offering robust predictive performance and inherent interpretability across various domains, including healthcare, finance, and logistics. However, current tree induction methods often face…

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this…

Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performance improvements (on language modeling and image…

Retrieval augmented generation (RAG) reduces hallucinations and factual errors in large language models (LLMs) by conditioning generation on retrieved external knowledge. Recent search agents further cast RAG as an autonomous, multi-turn…

Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focused on improving effectiveness and user satisfaction,…

Neural architecture search (NAS) has brought significant progress in recent image recognition tasks. Most existing NAS methods apply restricted search spaces, which limits the upper-bound performance of searched models. To address this…

We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Bayesian optimization (BO) is a model-based approach to sequentially optimize expensive black-box functions, such as the validation error of a deep neural network with respect to its hyperparameters. In many real-world scenarios, the…

Evolutionary prompt search is a practical black-box approach for red teaming large language models, however existing methods often collapse onto a small family of high-performing prompts, limiting coverage of distinct failure modes. We…

Existing multilingual embedding models often encounter challenges in cross-lingual scenarios due to imbalanced linguistic resources and less consideration of cross-lingual alignment during training. Although standardized contrastive…

Artificial neural network (NN) architecture design is a nontrivial and time-consuming task that often requires a high level of human expertise. Neural architecture search (NAS) serves to automate the design of NN architectures and has…

Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this…

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…

Large language model (LLM)-based embedding models, benefiting from large scale pre-training and post-training, have begun to surpass BERT and T5-based models on general-purpose text embedding tasks such as document retrieval. However, a…

Causal inference is central to scientific discovery, yet choosing appropriate methods remains challenging because of the complexity of both statistical methodology and real-world data. Inspired by the success of artificial intelligence in…

We propose EVOlutionary Selector (EVOS), an efficient training paradigm for accelerating Implicit Neural Representation (INR). Unlike conventional INR training that feeds all samples through the neural network in each iteration, our…

We study the problem of learning a good search policy for combinatorial search spaces. We propose retrospective imitation learning, which, after initial training by an expert, improves itself by learning from \textit{retrospective…

Molecular discovery, when formulated as an optimization problem, presents significant computational challenges because optimization objectives can be non-differentiable. Evolutionary Algorithms (EAs), often used to optimize black-box…