Large language models (LLMs) predominantly employ decoder-only transformer architectures, necessitating the retention of keys/values information for historical tokens to provide contextual information and avoid redundant computation. However, the substantial size and parameter volume of these LLMs require massive GPU memory. This memory demand increases with the length of the input text, leading to an urgent need for more efficient methods of information storage and processing. This study introduces Anchor-based LLMs (AnLLMs), which utilize an innovative anchor-based self-attention network (AnSAN) and also an anchor-based inference strategy. This approach enables LLMs to compress sequence information into an anchor token, reducing the keys/values cache and enhancing inference efficiency. Experiments on question-answering benchmarks reveal that AnLLMs maintain similar accuracy levels while achieving up to 99% keys/values cache reduction and up to 3.5 times faster inference. Despite a minor compromise in accuracy, the substantial enhancements of AnLLMs employing the AnSAN technique in resource utilization and computational efficiency underscore their potential for practical LLM applications.

Large Language Models (LLMs) have demonstrated exceptional proficiency in language-related tasks, but their deployment poses significant challenges due to substantial memory and storage requirements. Weight-only quantization has emerged as a promising solution to address these challenges. Previous research suggests that fine-tuning through up and down rounding can enhance performance. In this study, we introduce SignRound, a method that utilizes signed gradient descent (SignSGD) to optimize rounding values and weight clipping within just 200 steps. SignRound integrates the advantages of Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ), achieving exceptional results across 2 to 4 bits while maintaining low tuning costs and avoiding additional inference overhead. For example, SignRound achieves absolute average accuracy improvements ranging from 6.91% to 33.22% at 2 bits, as measured by the average zero-shot accuracy across 11 tasks. It also demonstrates strong generalization to recent models, achieving near-lossless 4-bit quantization in most scenarios. The source code will be made publicly available.

Dense retrieval systems are commonly used for information retrieval (IR). They rely on learning text representations through an encoder and usually require supervised modeling via labelled data which can be costly to obtain or simply unavailable. In this study, we introduce a novel unsupervised text representation learning technique via instruction-tuning the pre-trained encoder-decoder large language model (LLM) under the dual-encoder retrieval framework. We demonstrate on multiple languages that the corpus representation can be augmented by the representations of relevant synthetic queries generated by the instruct-tuned LLM founded on the Rao-Blackwell theorem. Furthermore, we effectively align the query and corpus text representation with self-instruct tuning. We evaluate our proposed method under low-resource settings on three English, two German and one Portuguese retrieval datasets measuring NDCG@10, MRR@100, Recall@100. We significantly improve the average zero-shot retrieval performance on all metrics, increasing out-of-box FLAN-T5 model variations by [4.73%, 6.15%] in absolute NDCG@10 and exceeding four supervised dense retrievers.

In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved. This may result in intent classification and slot tagging errors. In this work, we propose to leverage Entity Resolution (ER) features in NLU reranking and introduce a novel loss term based on ER signals to better learn model weights in the reranking framework. In addition, for a multi-domain dialog scenario, we propose a score distribution matching method to ensure scores generated by the NLU reranking models for different domains are properly calibrated. In offline experiments, we demonstrate our proposed approach significantly outperforms the baseline model on both single-domain and cross-domain evaluations.