Retrieval-Augmented Generation (RAG) is a crucial method for mitigating hallucinations in Large Language Models (LLMs) and integrating external knowledge into their responses. Existing RAG methods typically employ query rewriting to clarify the user intent and manage multi-hop logic, while using hybrid retrieval to expand search scope. However, the tight coupling of query rewriting to the dense retriever limits its compatibility with hybrid retrieval, impeding further RAG performance improvements. To address this challenge, we introduce a high-level searcher that decomposes complex queries into atomic queries, independent of any retriever-specific optimizations. Additionally, to harness the strengths of sparse retrievers for precise keyword retrieval, we have developed a new sparse searcher that employs Lucene syntax to enhance retrieval accuracy.Alongside web and dense searchers, these components seamlessly collaborate within our proposed method, \textbf{LevelRAG}. In LevelRAG, the high-level searcher orchestrates the retrieval logic, while the low-level searchers (sparse, web, and dense) refine the queries for optimal retrieval. This approach enhances both the completeness and accuracy of the retrieval process, overcoming challenges associated with current query rewriting techniques in hybrid retrieval scenarios. Empirical experiments conducted on five datasets, encompassing both single-hop and multi-hop question answering tasks, demonstrate the superior performance of LevelRAG compared to existing RAG methods. Notably, LevelRAG outperforms the state-of-the-art proprietary model, GPT4o, underscoring its effectiveness and potential impact on the RAG field.

The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and textual instructions into the context of large language models (LLMs), where large-scale parameters and numerous context tokens (predominantly vision tokens) result in substantial computational overhead. Previous efforts towards efficient LMMs always focus on replacing the LLM backbone with smaller models, while neglecting the crucial issue of token quantity. In this paper, we introduce LLaVA-Mini, an efficient LMM with minimal vision tokens. To achieve a high compression ratio of vision tokens while preserving visual information, we first analyze how LMMs understand vision tokens and find that most vision tokens only play a crucial role in the early layers of LLM backbone, where they mainly fuse visual information into text tokens. Building on this finding, LLaVA-Mini introduces modality pre-fusion to fuse visual information into text tokens in advance, thereby facilitating the extreme compression of vision tokens fed to LLM backbone into one token. LLaVA-Mini is a unified large multimodal model that can support the understanding of images, high-resolution images, and videos in an efficient manner. Experiments across 11 image-based and 7 video-based benchmarks demonstrate that LLaVA-Mini outperforms LLaVA-v1.5 with just 1 vision token instead of 576. Efficiency analyses reveal that LLaVA-Mini can reduce FLOPs by 77%, deliver low-latency responses within 40 milliseconds, and process over 10,000 frames of video on the GPU hardware with 24GB of memory.

Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policy-makers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propose a novel LLM-driven Simultaneous Generation (LSG) framework, which allows the off-the-shelf LLM to decide the generation timing and produce output concurrently. Specifically, LSG selects the generation policy that minimizes latency as the baseline policy. Referring to the baseline policy, LSG enables the LLM to devise an improved generation policy that better balances latency and generation quality, and writes generation results accordingly. Experiments on simultaneous translation and streaming automatic speech recognition tasks show that our method can achieve state-of-the-art performance utilizing the open-source LLMs and demonstrate practicality in real-world scenarios.

The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance. However, incorrect understanding of the sentence to be translated can degrade translation quality. To address this issue, we proposed a novel Iterative Bilingual Understanding Translation (IBUT) method based on the cross-lingual capabilities of LLMs and the dual characteristics of translation tasks. The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. Furthermore, the dual characteristics allow IBUT to generate effective cross-lingual feedback, iteratively refining contextual understanding, thereby reducing errors and improving translation performance. Experimental results showed that the proposed IBUT outperforms several strong comparison methods, especially being generalized to multiple domains (e.g., news, commonsense, and cultural translation benchmarks).

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leaving low-resource languages with weaker generative capabilities and relatively limited knowledge. Enhancing the multilingual capabilities of LLMs is therefore crucial for serving over 100 linguistic communities worldwide. An intuitive approach to enhance the multilingual capabilities would be to construct instruction data for various languages, but constructing instruction data for over 100 languages is prohibitively costly. In this paper, we introduce BayLing 2, which efficiently transfers generative capabilities and knowledge from high-resource languages to low-resource languages through language alignment. To achieve this, we constructed a dataset of 3.2 million instructions, comprising high-resource language instructions (Chinese and English) and cross-lingual instructions for 100+ languages and performed instruction tuning based on the dataset to facilitate the capability transfer between languages. Using Llama as the foundation model, we developed BayLing-2-7B, BayLing-2-13B, and BayLing-2-8B, and conducted a comprehensive evaluation of BayLing. For multilingual translation across 100+ languages, BayLing shows superior performance compared to open-source models of similar scale. For multilingual knowledge and understanding benchmarks, BayLing achieves significant improvements across over 20 low-resource languages, demonstrating its capability of effective knowledge transfer from high-resource to low-resource languages. Furthermore, results on English benchmarks indicate that BayLing maintains high performance in highresource languages while enhancing the performance in low-resource languages. Demo, homepage, code and models of BayLing are available.

Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation (RAG). Existing work typically employs few-shot prompting or manually constructed rules to implement iterative retrieval. This introduces additional inference overhead and overlooks the remarkable reasoning capabilities of Large Language Models (LLMs). In this paper, we introduce Auto-RAG, an autonomous iterative retrieval model centered on the LLM's powerful decision-making capabilities. Auto-RAG engages in multi-turn dialogues with the retriever, systematically planning retrievals and refining queries to acquire valuable knowledge. This process continues until sufficient external information is gathered, at which point the results are presented to the user. To this end, we develop a method for autonomously synthesizing reasoning-based decision-making instructions in iterative retrieval and fine-tuned the latest open-source LLMs. The experimental results indicate that Auto-RAG is capable of autonomous iterative interaction with the retriever, effectively leveraging the remarkable reasoning and decision-making abilities of LLMs, which lead to outstanding performance across six benchmarks. Further analysis reveals that Auto-RAG can autonomously adjust the number of iterations based on the difficulty of the questions and the utility of the retrieved knowledge, without requiring any human intervention. Moreover, Auto-RAG expresses the iterative retrieval process in natural language, enhancing interpretability while providing users with a more intuitive experience\footnote{Code is available at \url{https://github.com/ictnlp/Auto-RAG}.

Streaming generation models are increasingly utilized across various fields, with the Transducer architecture being particularly popular in industrial applications. However, its input-synchronous decoding mechanism presents challenges in tasks requiring non-monotonic alignments, such as simultaneous translation, leading to suboptimal performance in these contexts. In this research, we address this issue by tightly integrating Transducer's decoding with the history of input stream via a learnable monotonic attention mechanism. Our approach leverages the forwardbackward algorithm to infer the posterior probability of alignments between the predictor states and input timestamps, which is then used to estimate the context representations of monotonic attention in training. This allows Transducer models to adaptively adjust the scope of attention based on their predictions, avoiding the need to enumerate the exponentially large alignment space. Extensive experiments demonstrate that our MonoAttn-Transducer significantly enhances the handling of non-monotonic alignments in streaming generation, offering a robust solution for Transducer-based frameworks to tackle more complex streaming generation tasks. Unlike modern turn-based large language models, streaming models need to start generating the output before the input is completely read. Popular streaming generation methods can be broadly divided into two categories: Attentionbased Encoder-Decoder (AED; Bahdanau et al., 2015) and Transducer (Graves, 2012). Streaming AED models adapt the conventional sequence-to-sequence framework (Bahdanau, 2014) to support streaming generation. They often rely on an external policy module to determine the READ/WRITE actions in inference and to direct the scope of cross-attention in training. Examples include Wait-k policy (Ma et al., 2019) and monotonic attention-based methods (Raffel et al., 2017; Arivazhagan et al., 2019; Ma et al., 2020d; 2023a).

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed.

MSC (Huang and Feng, 2024) argues that a byte should contribute to multiple neighboring Neural Machine Translation (NMT) is a consistently contexts, necessitating a multi-scale contextualization hot research topic, and recent years have approach. To this end, MSC groups hidden seen the growing significance of multilingual language state dimensions and assigns CNNs with different modeling (Zhang et al., 2023). The selection kernel sizes to each group. of tokenization and vocabulary is critical to Although MSC provides an effective framework multilingual language models, which plays an important for modeling multi-scale contextualization and role in vectorization of texts and discretization achieved state-of-the-art performance, it suffers of predicted hidden states. While some models from a significant limitation: the scales are manually (Costa-jussà et al., 2022; Dubey et al., 2024) predefined. This reduces the model's ability use large vocabularies to ensure word coverage, to generalize to multilingual scenarios, particularly others (Touvron et al., 2023; Jiang et al., 2023) opt in massively multilingual machine translation, for byte fallback strategy. This approach allows which may involve over 50 languages.

Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). However, careful evaluations by human reveal that the translations produced by LLMs still contain multiple errors. Importantly, feeding back such error information into the LLMs can lead to self-refinement and result in improved translation performance. Motivated by these insights, we introduce a systematic LLM-based self-refinement translation framework, named \textbf{TEaR}, which stands for \textbf{T}ranslate, \textbf{E}stimate, \textbf{a}nd \textbf{R}efine, marking a significant step forward in this direction. Our findings demonstrate that 1) our self-refinement framework successfully assists LLMs in improving their translation quality across a wide range of languages, whether it's from high-resource languages to low-resource ones or whether it's English-centric or centered around other languages; 2) TEaR exhibits superior systematicity and interpretability; 3) different estimation strategies yield varied impacts, directly affecting the effectiveness of the final corrections. Additionally, traditional neural translation models and evaluation models operate separately, often focusing on singular tasks due to their limited capabilities, while general-purpose LLMs possess the capability to undertake both tasks simultaneously. We further conduct cross-model correction experiments to investigate the potential relationship between the translation and evaluation capabilities of general-purpose LLMs. Our code and data are available at https://github.com/fzp0424/self_correct_mt