Related papers: Enhancing Systematic Decompositional Natural Langu…
Large Language Models (LLMs) have recently achieved remarkable progress by leveraging Reinforcement Learning and extended Chain-of-Thought (CoT) techniques. However, the challenge of performing efficient language reasoning--especially…
An outstanding image-text retrieval model depends on high-quality labeled data. While the builders of existing image-text retrieval datasets strive to ensure that the caption matches the linked image, they cannot prevent a caption from…
We present a novel approach for training small language models for reasoning-intensive document ranking that combines knowledge distillation with reinforcement learning optimization. While existing methods often rely on expensive human…
Multimodal embeddings are widely used in downstream tasks such as multimodal retrieval, enabling alignment of interleaved modalities in a shared representation space. While recent studies show that Multimodal Large Language Models (MLLMs)…
Pre-trained Language Models (PLMs) have been applied in NLP tasks and achieve promising results. Nevertheless, the fine-tuning procedure needs labeled data of the target domain, making it difficult to learn in low-resource and non-trivial…
Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the…
Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on intermediate…
Reliable uncertainty estimation has become a crucial requirement for the industrial deployment of deep learning algorithms, particularly in high-risk applications such as autonomous driving and medical diagnosis. However, mainstream…
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from…
Recent advancements in large language models (LLMs) have enhanced natural-language reasoning. However, their limited parametric memory and susceptibility to hallucination present persistent challenges for tasks requiring accurate,…
Deductive reasoning plays a pivotal role in the formulation of sound and cohesive arguments. It allows individuals to draw conclusions that logically follow, given the truth value of the information provided. Recent progress in the domain…
Effective code generation with language models hinges on two critical factors: accurately understanding the intent of the prompt and generating code that applies algorithmic reasoning to produce correct solutions capable of passing diverse…
When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into…
To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…
While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural…
\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but its reliability under noisy retrieval contexts remains…
Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query…
Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…
We introduce a neural network that represents sentences by composing their words according to induced binary parse trees. We use Tree-LSTM as our composition function, applied along a tree structure found by a fully differentiable natural…
A key paradigm to improve the reasoning capabilities of large language models (LLMs) is to allocate more inference-time compute to search against a verifier or reward model. This process can then be utilized to refine the pretrained model…