Ninglu Shao

Xiao Zhang, Ninglu Shao, Zihua Si et al.

Contextual batched bandit (CBB) is a setting where a batch of rewards is observed from the environment at the end of each episode, but the rewards of the non-executed actions are unobserved, resulting in partial-information feedback. Existing approaches for CBB often ignore the rewards of the non-executed actions, leading to underutilization of feedback information. In this paper, we propose an efficient approach called Sketched Policy Updating with Imputed Rewards (SPUIR) that completes the unobserved rewards using sketching, which approximates the full-information feedbacks. We formulate reward imputation as an imputation regularized ridge regression problem that captures the feedback mechanisms of both executed and non-executed actions. To reduce time complexity, we solve the regression problem using randomized sketching. We prove that our approach achieves an instantaneous regret with controllable bias and smaller variance than approaches without reward imputation. Furthermore, our approach enjoys a sublinear regret bound against the optimal policy. We also present two extensions, a rate-scheduled version and a version for nonlinear rewards, making our approach more practical. Experimental results show that SPUIR outperforms state-of-the-art baselines on synthetic, public benchmark, and real-world datasets.

Zheng Liu, Chenyuan Wu, Ninglu Shao et al.

The existing Retrieval-Augmented Generation (RAG) systems face significant challenges in terms of cost and effectiveness. On one hand, they need to encode the lengthy retrieved contexts before responding to the input tasks, which imposes substantial computational overhead. On the other hand, directly using generic Large Language Models (LLMs) often leads to sub-optimal answers, while task-specific fine-tuning may compromise the LLMs' general capabilities. To address these challenges, we introduce a novel approach called FlexRAG (Flexible Context Adaptation for RAG). In this approach, the retrieved contexts are compressed into compact embeddings before being encoded by the LLMs. Simultaneously, these compressed embeddings are optimized to enhance downstream RAG performance. A key feature of FlexRAG is its flexibility, which enables effective support for diverse compression ratios and selective preservation of important contexts. Thanks to these technical designs, FlexRAG achieves superior generation quality while significantly reducing running costs. Comprehensive experiments on various question-answering datasets validate our approach as a cost-effective and flexible solution for RAG systems.

Peitian Zhang, Zheng Liu, Shitao Xiao et al.

Long context compression is a critical research problem due to its significance in reducing the high computational and memory costs associated with LLMs. In this paper, we propose Activation Beacon, a plug-in module for transformer-based LLMs that targets effective, efficient, and flexible compression of long contexts. To achieve this, our method introduces the following technical designs. 1) We directly compress the activations (i.e. keys and values at every layer), rather than leveraging soft prompts to relay information (which constitute a major bottleneck to encapsulate the complex information within long contexts). 2) We tailor the compression workflow, where each fine-grained input unit is progressively compressed, enabling high-quality compression and efficient computation during both training and inference. 3) We train the model through compression-based auto-regression, making full use of plain texts and instructional data to optimize the model's compression performance. 4) During training, we randomly sample a compression ratio at each step, teaching the model to support a wide range of compression configurations. Extensive evaluations are conducted on various long-context tasks whose lengths (e.g., 128K) may far exceed the maximum training length (20K), such as document understanding, few-shot learning, and Needle-in-a-Haystack. Whilst existing methods struggle to handle these challenging tasks, Activation Beacon maintains a comparable performance to the uncompressed baseline across various scenarios, achieving a 2x acceleration in inference time and an 8x reduction of memory costs for KV cache. Our data, model, and code have been released at \url{https://github.com/FlagOpen/FlagEmbedding/}.

Peitian Zhang, Ninglu Shao, Zheng Liu et al.

We extend the context length of Llama-3-8B-Instruct from 8K to 80K via QLoRA fine-tuning. The entire training cycle is super efficient, which takes 8 hours on one 8xA800 (80G) GPU machine. The resulted model exhibits superior performances across a broad range of evaluation tasks, such as NIHS, topic retrieval, and long-context language understanding; meanwhile, it also well preserves the original capability over short contexts. The dramatic context extension is mainly attributed to merely 3.5K synthetic training samples generated by GPT-4 , which indicates the LLMs' inherent (yet largely underestimated) potential to extend its original context length. In fact, the context length could be extended far beyond 80K with more computation resources. Therefore, the team will publicly release the entire resources (including data, model, data generation pipeline, training code) so as to facilitate the future research from the community: \url{https://github.com/FlagOpen/FlagEmbedding}.

Ninglu Shao, Shitao Xiao, Zheng Liu et al.

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the information within a limited context. Although the size of context window can be extended by fine-tuning, it will result in a substantial cost in both training and inference stage. In this paper, we present Extensible Tokenization as an alternative method which realizes the flexible scaling of LLMs' context. Extensible Tokenization stands as a midware in between of the tokenized context and the LLM, which transforms the raw token embeddings into the extensible embeddings. Such embeddings provide a more compact representation for the long context, on top of which the LLM is able to perceive more information with the same context window. Extensible Tokenization is also featured by its flexibility: the scaling factor can be flexibly determined within a feasible scope, leading to the extension of an arbitrary context length at the inference time. Besides, Extensible Tokenization is introduced as a drop-in component, which can be seamlessly plugged into not only the LLM itself and but also its fine-tuned derivatives, bringing in the extended contextual information while fully preserving the LLM's existing capabilities. We perform comprehensive experiments on long-context language modeling and understanding tasks, which verify Extensible Tokenization as an effective, efficient, flexible, and compatible method to extend LLM's context. Our model and source code will be made publicly available.

Zhihao Zhu, Ninglu Shao, Defu Lian et al.

Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in retrieval-augmented generation. However, such a solution risks compromising privacy, as recent studies experimentally showed that the original text can be partially reconstructed from text embeddings by pre-trained language models. The significant advantage of LLMs over traditional pre-trained models may exacerbate these concerns. To this end, we investigate the effectiveness of reconstructing original knowledge and predicting entity attributes from these embeddings when LLMs are employed. Empirical findings indicate that LLMs significantly improve the accuracy of two evaluated tasks over those from pre-trained models, regardless of whether the texts are in-distribution or out-of-distribution. This underscores a heightened potential for LLMs to jeopardize user privacy, highlighting the negative consequences of their widespread use. We further discuss preliminary strategies to mitigate this risk.

Ninglu Shao, Shitao Xiao, Zheng Liu et al.

Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we propose Extensible Embedding, which realizes high-quality extension of LLM's context with strong flexibility and cost-effectiveness. Extensible embedding stand as an enhancement of typical token embedding, which represents the information for an extensible scope of context instead of a single token. By leveraging such compact input units of higher information density, the LLM can access to a vast scope of context even with a small context window. Extensible embedding is systematically optimized in architecture and training method, which leads to multiple advantages. 1) High flexibility of context extension, which flexibly supports ad-hoc extension of diverse context lengths. 2) Strong sample efficiency of training, which enables the embedding model to be learned in a cost-effective way. 3) Superior compatibility with the existing LLMs, where the extensible embedding can be seamlessly introduced as a plug-in component. Comprehensive evaluations on long-context language modeling and understanding tasks verify extensible embedding as an effective, efficient, flexible, and compatible method to extend the LLM's context.

Ninglu Shao, Jinshan Wang, Chenxu Wang et al.

Currently, short video platforms have become the primary place for individuals to share experiences and obtain information. To better meet users' needs for acquiring information while browsing short videos, some apps have introduced a search entry at the bottom of videos, accompanied with recommended relevant queries. This scenario is known as query recommendation in video-related search, where core task is item-to-query (I2Q) recommendation. As this scenario has only emerged in recent years, there is a notable scarcity of academic research and publicly available datasets in this domain. To address this gap, we systematically examine the challenges associated with this scenario for the first time. Subsequently, we release a large-scale dataset derived from real-world data pertaining to the query recommendation in video-\textit{\textbf{r}}elated \textit{\textbf{s}}earch on the \textit{\textbf{Kuai}}shou app (\textbf{KuaiRS}). Presently, existing methods rely on embeddings to calculate similarity for matching short videos with queries, lacking deep interaction between the semantic content and the query. In this paper, we introduce a novel LLM-based framework named \textbf{GREAT}, which \textit{\textbf{g}}uides que\textit{\textbf{r}}y g\textit{\textbf{e}}ner\textit{\textbf{a}}tion with a \textit{\textbf{t}}rie to address I2Q recommendation in related search. Specifically, we initially gather high-quality queries with high exposure and click-through rate to construct a query-based trie. During training, we enhance the LLM's capability to generate high-quality queries using the query-based trie. In the inference phase, the query-based trie serves as a guide for the token generation. Finally, we further refine the relevance and literal quality between items and queries via a post-processing module. Extensive offline and online experiments demonstrate the effectiveness of our proposed method.