Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations

Structured pruning fundamentally reduces computational and memory overheads of large language models (LLMs) and offers a feasible solution for end-side LLM deployment. Structurally pruned models remain dense and high-precision, highly compatible with further tuning and compression. However, as the coarse-grained structured pruning poses large damage to the highly interconnected model, achieving a high compression ratio for scaled-up LLMs remains a challenge. In this paper, we introduce a task-agnostic structured pruning approach coupled with a compact Transformer architecture design. The proposed approach, named TransAct, reduces transitional activations inside multi-head attention (MHA) and multi-layer perceptron (MLP) modules, while preserving the inter-module activations that are sensitive to perturbations. Hence, the LLM is pruned into an intra-module low-rank architecture, significantly reducing weights, KV Cache and attention computation. TransAct is implemented on the LLaMA model and evaluated on downstream benchmarks. Results verify the optimality of our approach at high compression with respect to both efficiency and performance. Further, ablation studies reveal the strength of activation-guided iterative pruning and provide experimental analysis on the redundancy of MHA and MLP modules.

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents

With the remarkable advancements of large language models (LLMs), LLM-based agents have become a research hotspot in human-computer interaction. However, there is a scarcity of benchmarks available for LLM-based mobile agents. Benchmarking these agents generally faces three main challenges: (1) The inefficiency of UI-only operations imposes limitations to task evaluation. (2) Specific instructions within a singular application lack adequacy for assessing the multi-dimensional reasoning and decision-making capacities of LLM mobile agents. (3) Current evaluation metrics are insufficient to accurately assess the process of sequential actions. To this end, we propose Mobile-Bench, a novel benchmark for evaluating the capabilities of LLM-based mobile agents. First, we expand conventional UI operations by incorporating 103 collected APIs to accelerate the efficiency of task completion. Subsequently, we collect evaluation data by combining real user queries with augmentation from LLMs. To better evaluate different levels of planning capabilities for mobile agents, our data is categorized into three distinct groups: SAST, SAMT, and MAMT, reflecting varying levels of task complexity. Mobile-Bench comprises 832 data entries, with more than 200 tasks specifically designed to evaluate multi-APP collaboration scenarios. Furthermore, we introduce a more accurate evaluation metric, named CheckPoint, to assess whether LLM-based mobile agents reach essential points during their planning and reasoning steps.

SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, an innovative architecture that extends the core decoder-only framework by incorporating subsampling, upsampling, and bypass modules. The subsampling modules are responsible for shortening the sequence, while the upsampling modules restore the sequence length, and the bypass modules enhance convergence. In comparison to LLaMA, the proposed SUBLLM exhibits significant enhancements in both training and inference speeds as well as memory usage, while maintaining competitive few-shot performance. During training, SUBLLM increases speeds by 26% and cuts memory by 10GB per GPU. In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU. The training and inference speeds can be enhanced by 34% and 52% respectively when the context window is expanded to 8192. We shall release the source code of the proposed architecture in the published version.

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval

Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous studies have proposed retrieving suitable tools for the LLM based on the user query. However, previously proposed methods do not consider the differences between seen and unseen tools, nor do they take the hierarchy of the tool library into account, which may lead to suboptimal performance for tool retrieval. Therefore, to address the aforementioned issues, we propose ToolRerank, an adaptive and hierarchy-aware reranking method for tool retrieval to further refine the retrieval results. Specifically, our proposed ToolRerank includes Adaptive Truncation, which truncates the retrieval results related to seen and unseen tools at different positions, and Hierarchy-Aware Reranking, which makes retrieval results more concentrated for single-tool queries and more diverse for multi-tool queries. Experimental results show that ToolRerank can improve the quality of the retrieval results, leading to better execution results generated by the LLM.

A Comprehensive Evaluation of Quantization Strategies for Large Language Models

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques, which reduce the bits needed for model weights or activations with minimal performance loss, have become popular due to the rise of LLMs. However, most quantization studies use pre-trained LLMs, and the impact of quantization on instruction-tuned LLMs and the relationship between perplexity and benchmark performance of quantized LLMs are not well understood. Evaluation of quantized LLMs is often limited to language modeling and a few classification tasks, leaving their performance on other benchmarks unclear. To address these gaps, we propose a structured evaluation framework consisting of three critical dimensions: (1) knowledge \& capacity, (2) alignment, and (3) efficiency, and conduct extensive experiments across ten diverse benchmarks. Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks. Furthermore, quantized LLMs with larger parameter scales can outperform smaller LLMs. Despite the memory savings achieved through quantization, it can also slow down the inference speed of LLMs. Consequently, substantial engineering efforts and hardware support are imperative to achieve a balanced optimization of decoding speed and memory consumption in the context of quantized LLMs.

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming to help users efficiently obtain information and execute tasks, and provide users with more intelligent, convenient, and rich interaction experiences. With the development of smartphones and IoT, computing and sensing devices have become ubiquitous, greatly expanding the boundaries of IPAs. However, due to the lack of capabilities such as user intent understanding, task planning, tool using, and personal data management etc., existing IPAs still have limited practicality and scalability. Recently, the emergence of foundation models, represented by large language models (LLMs), brings new opportunities for the development of IPAs. With the powerful semantic understanding and reasoning capabilities, LLM can enable intelligent agents to solve complex problems autonomously. In this paper, we focus on Personal LLM Agents, which are LLM-based agents that are deeply integrated with personal data and personal devices and used for personal assistance. We envision that Personal LLM Agents will become a major software paradigm for end-users in the upcoming era. To realize this vision, we take the first step to discuss several important questions about Personal LLM Agents, including their architecture, capability, efficiency and security. We start by summarizing the key components and design choices in the architecture of Personal LLM Agents, followed by an in-depth analysis of the opinions collected from domain experts. Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.

CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training

Simultaneous machine translation (SiMT) is a challenging task that requires starting translation before the full source sentence is available. Prefix-to-prefix framework is often applied to SiMT, which learns to predict target tokens using only a partial source prefix. However, due to the word order difference between languages, misaligned prefix pairs would make SiMT models suffer from serious hallucination problems, i.e. target outputs that are unfaithful to source inputs. Such problems can not only produce target tokens that are not supported by the source prefix, but also hinder generating the correct translation by receiving more source words. In this work, we propose a Confidence-Based Simultaneous Machine Translation (CBSiMT) framework, which uses model confidence to perceive hallucination tokens and mitigates their negative impact with weighted prefix-to-prefix training. Specifically, token-level and sentence-level weights are calculated based on model confidence and acted on the loss function. We explicitly quantify the faithfulness of the generated target tokens using the token-level weight, and employ the sentence-level weight to alleviate the disturbance of sentence pairs with serious word order differences on the model. Experimental results on MuST-C English-to-Chinese and WMT15 German-to-English SiMT tasks demonstrate that our method can consistently improve translation quality at most latency regimes, with up to 2 BLEU scores improvement at low latency.

From Indeterminacy to Determinacy: Augmenting Logical Reasoning Capabilities with Large Language Models

Recent advances in LLMs have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior works focus on modeling reasoning steps using specific thought structures like chains, trees, or graphs. However, LLM-based reasoning continues to encounter three challenges: 1) Selecting appropriate reasoning structures for various tasks; 2) Exploiting known conditions sufficiently and efficiently to deduce new insights; 3) Considering the impact of historical reasoning experience. To address these challenges, we propose DetermLR, a novel reasoning framework that formulates the reasoning process as a transformational journey from indeterminate premises to determinate ones. This process is marked by the incremental accumulation of determinate premises, making the conclusion progressively closer to clarity. DetermLR includes three essential components: 1) Premise identification: We categorize premises into two distinct types: determinate and indeterminate. This empowers LLMs to customize reasoning structures to match the specific task complexities. 2) Premise prioritization and exploration: We leverage quantitative measurements to assess the relevance of each premise to the target, prioritizing more relevant premises for exploring new insights. 3) Iterative process with reasoning memory: We introduce a reasoning memory module to automate storage and extraction of available premises and reasoning paths, preserving historical reasoning details for more accurate premise prioritization. Comprehensive experimental results show that DetermLR outperforms all baselines on four challenging logical reasoning tasks: LogiQA, ProofWriter, FOLIO, and LogicalDeduction. DetermLR can achieve better reasoning performance while requiring fewer visited states, highlighting its superior efficiency and effectiveness in tackling logical reasoning tasks.

CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?

We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1.7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams. This dataset aims to provide a benchmark tool for assessing the following question: to what grade level of elementary school math do the abilities of popular large language models (LLMs) correspond? We evaluate a variety of popular LLMs, including both commercial and open-source options, and discover that only GPT-4 achieves success (accuracy $\geq$ 60\%) across all six elementary school grades, while other models falter at different grade levels. Furthermore, we assess the robustness of several top-performing LLMs by augmenting the original problems in the CMATH dataset with distracting information. Our findings reveal that GPT-4 is able to maintains robustness, while other model fail. We anticipate that our study will expose limitations in LLMs' arithmetic and reasoning capabilities, and promote their ongoing development and advancement.

UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning

Open-domain long-term memory conversation can establish long-term intimacy with humans, and the key is the ability to understand and memorize long-term dialogue history information. Existing works integrate multiple models for modelling through a pipeline, which ignores the coupling between different stages. In this paper, we propose a Unified framework for Long-term Memory Conversations (UniMC), which increases the connection between different stages by learning relevance representation. Specifically, we decompose the main task into three subtasks based on probability graphs: 1) conversation summarization, 2) memory retrieval, 3) memory-augmented generation. Each subtask involves learning a representation for calculating the relevance between the query and memory, which is modelled by inserting a special token at the beginning of the decoder input. The relevance representation learning strengthens the connection across subtasks through parameter sharing and joint training. Extensive experimental results show that the proposed method consistently improves over strong baselines and yields better dialogue consistency and engagingness.