arXiv subjects

Ji-Rong Wen

Publications and source records attributed to Ji-Rong Wen.

At least 217 records · Page 12Linked to original sources

arXiv2024

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought structures like chains, trees, or graphs. However, LLM-based reasoning still encounters the following challenges: (1) Limited adaptability of preset structures to diverse tasks; (2) Insufficient precision in exploiting known conditions to derive new ones; and (3) Inadequate consideration of historical reasoning experiences for subsequent reasoning steps. To this end, we propose DetermLR, a novel perspective that rethinks the reasoning process as an evolution from indeterminacy to determinacy. First, we categorize known conditions into two types: determinate and indeterminate premises This provides an oveall direction for the reasoning process and guides LLMs in converting indeterminate data into progressively determinate insights. Subsequently, we leverage quantitative measurements to prioritize more relevant premises to explore new insights. Furthermore, we automate the storage and extraction of available premises and reasoning paths with reasoning memory, preserving historical reasoning details for subsequent reasoning steps. Comprehensive experimental results demonstrate that DetermLR surpasses all baselines on various logical reasoning benchmarks: LogiQA, ProofWriter, FOLIO, PrOntoQA, and LogicalDeduction. Compared to previous multi-step reasoning methods, DetermLR achieves higher accuracy with fewer reasoning steps, highlighting its superior efficiency and effectiveness in solving logical reasoning tasks.

cs.AI↗

arXiv2024

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models

In this paper, we delve into several mechanisms employed by Transformer-based language models (LLMs) for factual recall tasks. We outline a pipeline consisting of three major steps: (1) Given a prompt ``The capital of France is,'' task-specific attention heads extract the topic token, such as ``France,'' from the context and pass it to subsequent MLPs. (2) As attention heads' outputs are aggregated with equal weight and added to the residual stream, the subsequent MLP acts as an ``activation,'' which either erases or amplifies the information originating from individual heads. As a result, the topic token ``France'' stands out in the residual stream. (3) A deep MLP takes ``France'' and generates a component that redirects the residual stream towards the direction of the correct answer, i.e., ``Paris.'' This procedure is akin to applying an implicit function such as ``get\_capital($X$),'' and the argument $X$ is the topic token information passed by attention heads. To achieve the above quantitative and qualitative analysis for MLPs, we proposed a novel analytic method aimed at decomposing the outputs of the MLP into components understandable by humans. Additionally, we observed a universal anti-overconfidence mechanism in the final layer of models, which suppresses correct predictions. We mitigate this suppression by leveraging our interpretation to improve factual recall confidence. The above interpretations are evaluated across diverse tasks spanning various domains of factual knowledge, using various language models from the GPT-2 families, 1.3B OPT, up to 7B Llama-2, and in both zero- and few-shot setups.

cs.CL↗

arXiv2024

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale math-related texts for pre-training, or relies on stronger LLMs (\eg GPT-4) to synthesize massive math problems. Both types of work generally lead to large costs in training or synthesis. To reduce the cost, based on open-source available texts, we propose an efficient way that trains a small LLM for math problem synthesis, to efficiently generate sufficient high-quality pre-training data. To achieve it, we create a dataset using GPT-4 to distill its data synthesis capability into the small LLM. Concretely, we craft a set of prompts based on human education stages to guide GPT-4, to synthesize problems covering diverse math knowledge and difficulty levels. Besides, we adopt the gradient-based influence estimation method to select the most valuable math-related texts. The both are fed into GPT-4 for creating the knowledge distillation dataset to train the small LLM. We leverage it to synthesize 6 million math problems for pre-training our JiuZhang3.0 model, which only needs to invoke GPT-4 API 9.3k times and pre-train on 4.6B data. Experimental results have shown that JiuZhang3.0 achieves state-of-the-art performance on several mathematical reasoning datasets, under both natural language reasoning and tool manipulation settings. Our code and data will be publicly released in \url{https://github.com/RUCAIBox/JiuZhang3.0}.

cs.CL↗

arXiv2024

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression

Key-value~(KV) caching is an important technique to accelerate the inference of large language models~(LLMs), but incurs significant memory overhead. To compress the size of KV cache, existing methods often compromise precision or require extra data for calibration, limiting their practicality in LLM deployment. In this paper, we introduce \textbf{DecoQuant}, a novel data-free low-bit quantization technique based on tensor decomposition methods, to effectively compress KV cache. Our core idea is to adjust the outlier distribution of the original matrix by performing tensor decomposition, so that the quantization difficulties are migrated from the matrix to decomposed local tensors. Specially, we find that outliers mainly concentrate on small local tensors, while large tensors tend to have a narrower value range. Based on this finding, we propose to apply low-bit quantization to the large tensor, while maintaining high-precision representation for the small tensor. Furthermore, we utilize the proposed quantization method to compress the KV cache of LLMs to accelerate the inference and develop an efficient dequantization kernel tailored specifically for DecoQuant. Through extensive experiments, DecoQuant demonstrates remarkable efficiency gains, showcasing up to a $\sim$75\% reduction in memory footprint while maintaining comparable generation quality.

cs.CL↗

arXiv2024

A Survey on the Memory Mechanism of Large Language Model based Agents

Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions. The key component to support agent-environment interactions is the memory of the agents. While previous studies have proposed many promising memory mechanisms, they are scattered in different papers, and there lacks a systematical review to summarize and compare these works from a holistic perspective, failing to abstract common and effective designing patterns for inspiring future studies. To bridge this gap, in this paper, we propose a comprehensive survey on the memory mechanism of LLM-based agents. In specific, we first discuss ''what is'' and ''why do we need'' the memory in LLM-based agents. Then, we systematically review previous studies on how to design and evaluate the memory module. In addition, we also present many agent applications, where the memory module plays an important role. At last, we analyze the limitations of existing work and show important future directions. To keep up with the latest advances in this field, we create a repository at \url{https://github.com/nuster1128/LLM_Agent_Memory_Survey}.

cs.AI↗

arXiv2024

Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation

Recently, large language models (LLMs) have shown great potential in recommender systems, either improving existing recommendation models or serving as the backbone. However, there exists a large semantic gap between LLMs and recommender systems, since items to be recommended are often indexed by discrete identifiers (item ID) out of the LLM's vocabulary. In essence, LLMs capture language semantics while recommender systems imply collaborative semantics, making it difficult to sufficiently leverage the model capacity of LLMs for recommendation. To address this challenge, in this paper, we propose a new LLM-based recommendation model called LC-Rec, which can better integrate language and collaborative semantics for recommender systems. Our approach can directly generate items from the entire item set for recommendation, without relying on candidate items. Specifically, we make two major contributions in our approach. For item indexing, we design a learning-based vector quantization method with uniform semantic mapping, which can assign meaningful and non-conflicting IDs (called item indices) for items. For alignment tuning, we propose a series of specially designed tuning tasks to enhance the integration of collaborative semantics in LLMs. Our fine-tuning tasks enforce LLMs to deeply integrate language and collaborative semantics (characterized by the learned item indices), so as to achieve an effective adaptation to recommender systems. Extensive experiments demonstrate the effectiveness of our method, showing that our approach can outperform a number of competitive baselines including traditional recommenders and existing LLM-based recommenders. Our code is available at https://github.com/RUCAIBox/LC-Rec/.

cs.IR↗

arXiv2024

Towards Coarse-to-Fine Evaluation of Inference Efficiency for Large Language Models

In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide application of LLMs, the inference efficiency is an essential concern, which has been widely studied in existing work, and numerous optimization algorithms and code libraries have been proposed to improve it. Nonetheless, users still find it challenging to compare the effectiveness of all the above methods and understand the underlying mechanisms. In this work, we perform a detailed coarse-to-fine analysis of the inference performance of various code libraries. To evaluate the overall effectiveness, we examine four usage scenarios within two practical applications. We further provide both theoretical and empirical fine-grained analyses of each module in the Transformer architecture. Our experiments yield comprehensive results that are invaluable for researchers to evaluate code libraries and improve inference strategies.

cs.CL↗

arXiv2024

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

Alignment with human preference is a desired property of large language models (LLMs). Currently, the main alignment approach is based on reinforcement learning from human feedback (RLHF). Despite the effectiveness of RLHF, it is intricate to implement and train, thus recent studies explore how to develop alternative alignment approaches based on supervised fine-tuning (SFT). A major limitation of SFT is that it essentially does imitation learning, which cannot fully understand what are the expected behaviors. To address this issue, we propose an improved alignment approach named FIGA. Different from prior methods, we incorporate fine-grained (i.e., token or phrase level) quality signals that are derived by contrasting good and bad responses. Our approach has made two major contributions. Firstly, we curate a refined alignment dataset that pairs initial responses and the corresponding revised ones. Secondly, we devise a new loss function can leverage fine-grained quality signals to instruct the learning of LLMs for alignment. Extensive experiments have demonstrated the effectiveness of our approaches by comparing a number of competitive baselines.

cs.CL↗

arXiv2024

Dynamic Prompt Optimizing for Text-to-Image Generation

Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts. Users assign weights or alter the injection time steps of certain words in the text prompts to improve the quality of generated images. However, the success of fine-control prompts depends on the accuracy of the text prompts and the careful selection of weights and time steps, which requires significant manual intervention. To address this, we introduce the \textbf{P}rompt \textbf{A}uto-\textbf{E}diting (PAE) method. Besides refining the original prompts for image generation, we further employ an online reinforcement learning strategy to explore the weights and injection time steps of each word, leading to the dynamic fine-control prompts. The reward function during training encourages the model to consider aesthetic score, semantic consistency, and user preferences. Experimental results demonstrate that our proposed method effectively improves the original prompts, generating visually more appealing images while maintaining semantic alignment. Code is available at https://github.com/Mowenyii/PAE.

cs.CV↗

arXiv2024

EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention

To capture user preference, transformer models have been widely applied to model sequential user behavior data. The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a sequence. Due to the permutation-equivariant nature, positional encoding is used to enhance the attention between token representations. In this setting, the pairwise attention scores can be derived by both semantic difference and positional difference. However, prior studies often model the two kinds of difference measurements in different ways, which potentially limits the expressive capacity of sequence modeling. To address this issue, this paper proposes a novel transformer variant with complex vector attention, named EulerFormer, which provides a unified theoretical framework to formulate both semantic difference and positional difference. The EulerFormer involves two key technical improvements. First, it employs a new transformation function for efficiently transforming the sequence tokens into polar-form complex vectors using Euler's formula, enabling the unified modeling of both semantic and positional information in a complex rotation form.Secondly, it develops a differential rotation mechanism, where the semantic rotation angles can be controlled by an adaptation function, enabling the adaptive integration of the semantic and positional information according to the semantic contexts.Furthermore, a phase contrastive learning task is proposed to improve the isotropy of contextual representations in EulerFormer. Our theoretical framework possesses a high degree of completeness and generality. It is more robust to semantic variations and possesses moresuperior theoretical properties in principle. Extensive experiments conducted on four public datasets demonstrate the effectiveness and efficiency of our approach.

cs.IR↗

arXiv2024

Supporting Vision-Language Model Inference with Confounder-pruning Knowledge Prompt

Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models, recent works adopt fixed or learnable prompts, i.e., classification weights are synthesized from natural language describing task-relevant categories, to reduce the gap between tasks in the training and test phases. However, how and what prompts can improve inference performance remains unclear. In this paper, we explicitly clarify the importance of including semantic information in prompts, while existing prompting methods generate prompts without exploring the semantic information of textual labels. Manually constructing prompts with rich semantics requires domain expertise and is extremely time-consuming. To cope with this issue, we propose a semantic-aware prompt learning method, namely CPKP, which retrieves an ontological knowledge graph by treating the textual label as a query to extract task-relevant semantic information. CPKP further introduces a double-tier confounder-pruning procedure to refine the derived semantic information. The graph-tier confounders are gradually identified and phased out, inspired by the principle of Granger causality. The feature-tier confounders are demolished by following the maximum entropy principle in information theory. Empirically, the evaluations demonstrate the effectiveness of CPKP, e.g., with two shots, CPKP outperforms the manual-prompt method by 4.64% and the learnable-prompt method by 1.09% on average, and the superiority of CPKP in domain generalization compared to benchmark approaches. Our implementation is available at https://github.com/Mowenyii/CPKP.

cs.CV↗

arXiv2024

Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations

Information-seeking dialogue systems are widely used in e-commerce systems, with answers that must be tailored to fit the specific settings of the online system. Given the user query, the information-seeking dialogue systems first retrieve a subset of response candidates, then further select the best response from the candidate set through re-ranking. Current methods mainly retrieve response candidates based solely on the current query, however, incorporating similar questions could introduce more diverse content, potentially refining the representation and improving the matching process. Hence, in this paper, we proposed a Query-bag based Pseudo Relevance Feedback framework (QB-PRF), which constructs a query-bag with related queries to serve as pseudo signals to guide information-seeking conversations. Concretely, we first propose a Query-bag Selection module (QBS), which utilizes contrastive learning to train the selection of synonymous queries in an unsupervised manner by leveraging the representations learned from pre-trained VAE. Secondly, we come up with a Query-bag Fusion module (QBF) that fuses synonymous queries to enhance the semantic representation of the original query through multidimensional attention computation. We verify the effectiveness of the QB-PRF framework on two competitive pretrained backbone models, including BERT and GPT-2. Experimental results on two benchmark datasets show that our framework achieves superior performance over strong baselines.

cs.IR↗

arXiv2024

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting

Chain-of-Thought (CoT) prompting can enhance the reasoning capabilities of large language models (LLMs), establishing itself as a primary approach to solving complex reasoning tasks. Existing CoT synthesis approaches usually focus on simpler reasoning tasks and thus result in low-quality and inconsistent CoT prompts. In response to this challenge, we present an empirical investigation of CoT prompting and introduce CoTGenius, a novel framework designed for the automatic generation of superior CoT prompts. CoTGenius is developed based on three major evolution strategies, i.e., complicate, diversify, and specify-alongside two filtering mechanisms: evolutionary success judgement and correctness verification. We further employ CoTGenius to create an extensive CoT dataset, and subsequently fine-tune the Llama 2-Chat 7B and 13B models on this dataset. We call the resulting model ChainLM. To deal with the cumulative error issue in reasoning steps, we propose a step-level debating method, wherein multiple debaters discuss each reasoning step to arrive at the correct answer. Extensive experiments demonstrate that our ChainLM models exhibit enhanced proficiency in addressing a spectrum of complex reasoning problems compared to existing models. In addition, we conduct an in-depth analysis of the impact of data categories within CoTGenius on the model performance. We release our dataset and code at https://github.com/RUCAIBox/ChainLM.

cs.CL↗

arXiv2024

An Analysis on Matching Mechanisms and Token Pruning for Late-interaction Models

With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most dense retrieval models using a bi-encoder to encode each query or document into a dense vector, the recently proposed late-interaction multi-vector models (i.e., ColBERT and COIL) achieve state-of-the-art retrieval effectiveness by using all token embeddings to represent documents and queries and modeling their relevance with a sum-of-max operation. However, these fine-grained representations may cause unacceptable storage overhead for practical search systems. In this study, we systematically analyze the matching mechanism of these late-interaction models and show that the sum-of-max operation heavily relies on the co-occurrence signals and some important words in the document. Based on these findings, we then propose several simple document pruning methods to reduce the storage overhead and compare the effectiveness of different pruning methods on different late-interaction models. We also leverage query pruning methods to further reduce the retrieval latency. We conduct extensive experiments on both in-domain and out-domain datasets and show that some of the used pruning methods can significantly improve the efficiency of these late-interaction models without substantially hurting their retrieval effectiveness.

cs.IR↗

arXiv2024

BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models

Large language models (LLMs) have achieved dramatic proficiency over NLP tasks with normal length. Recently, multiple studies have committed to extending the context length and enhancing the long text modeling capabilities of LLMs. To comprehensively evaluate the long context ability of LLMs, we propose BAMBOO, a multi-task long context benchmark. BAMBOO has been designed with four principles: comprehensive capacity evaluation, avoidance of data contamination, accurate automatic evaluation, and different length levels. It consists of 10 datasets from 5 different long text understanding tasks, i.e. question answering, hallucination detection, text sorting, language modeling, and code completion, to cover core capacities and various domains of LLMs. We conduct experiments with five long context models on BAMBOO and further discuss four key research questions of long text. We also qualitatively analyze current long context models and point out future directions for enhancing long text modeling capacities. We release our data, prompts, and code at https://github.com/RUCAIBox/BAMBOO.

cs.CL↗

arXiv2024

Revisiting Local Computation of PageRank: Simple and Optimal

We revisit the classic local graph exploration algorithm ApproxContributions proposed by Andersen, Borgs, Chayes, Hopcroft, Mirrokni, and Teng (WAW '07, Internet Math. '08) for computing an $ε$-approximation of the PageRank contribution vector for a target node $t$ on a graph with $n$ nodes and $m$ edges. We give a worst-case complexity bound of ApproxContributions as $O(nπ(t)/ε\cdot\min(Δ_{in},Δ_{out},\sqrt{m}))$, where $π(t)$ is the PageRank score of $t$, and $Δ_{in}$ and $Δ_{out}$ are the maximum in-degree and out-degree of the graph, resp. We also give a lower bound of $Ω(\min(Δ_{in}/δ,Δ_{out}/δ,\sqrt{m}/δ,m))$ for detecting the $δ$-contributing set of $t$, showing that the simple ApproxContributions algorithm is already optimal. We also investigate the computational complexity of locally estimating a node's PageRank centrality. We improve the best-known upper bound of $\widetilde{O}(n^{2/3}\cdot\min(Δ_{out}^{1/3},m^{1/6}))$ given by Bressan, Peserico, and Pretto (SICOMP '23) to $O(n^{1/2}\cdot\min(Δ_{in}^{1/2},Δ_{out}^{1/2},m^{1/4}))$ by simply combining ApproxContributions with the Monte Carlo simulation method. We also improve their lower bound of $Ω(\min(n^{1/2}Δ_{out}^{1/2},n^{1/3}m^{1/3}))$ to $Ω(n^{1/2}\cdot\min(Δ_{in}^{1/2},Δ_{out}^{1/2},m^{1/4}))$ if $\min(Δ_{in},Δ_{out})=Ω(n^{1/3})$, and to $Ω(n^{1/2-γ}(\min(Δ_{in},Δ_{out}))^{1/2+γ})$ if $\min(Δ_{in},Δ_{out})=o(n^{1/3})$, where $γ>0$ is an arbitrarily small constant. Our matching upper and lower bounds resolve the open problem of whether one can tighten the bounds given by Bressan, Peserico, and Pretto (FOCS '18, SICOMP '23). Remarkably, the techniques and analyses for proving all our results are surprisingly simple.

cs.DS↗

arXiv2024

Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited

Designing spectral convolutional networks is a challenging problem in graph learning. ChebNet, one of the early attempts, approximates the spectral graph convolutions using Chebyshev polynomials. GCN simplifies ChebNet by utilizing only the first two Chebyshev polynomials while still outperforming it on real-world datasets. GPR-GNN and BernNet demonstrate that the Monomial and Bernstein bases also outperform the Chebyshev basis in terms of learning the spectral graph convolutions. Such conclusions are counter-intuitive in the field of approximation theory, where it is established that the Chebyshev polynomial achieves the optimum convergent rate for approximating a function. In this paper, we revisit the problem of approximating the spectral graph convolutions with Chebyshev polynomials. We show that ChebNet's inferior performance is primarily due to illegal coefficients learnt by ChebNet approximating analytic filter functions, which leads to over-fitting. We then propose ChebNetII, a new GNN model based on Chebyshev interpolation, which enhances the original Chebyshev polynomial approximation while reducing the Runge phenomenon. We conducted an extensive experimental study to demonstrate that ChebNetII can learn arbitrary graph convolutions and achieve superior performance in both full- and semi-supervised node classification tasks. Most notably, we scale ChebNetII to a billion graph ogbn-papers100M, showing that spectral-based GNNs have superior performance. Our code is available at https://github.com/ivam-he/ChebNetII.

cs.LG↗

arXiv2024

Efficient Algorithms for Personalized PageRank Computation: A Survey

Personalized PageRank (PPR) is a traditional measure for node proximity on large graphs. For a pair of nodes $s$ and $t$, the PPR value $π_s(t)$ equals the probability that an $α$-discounted random walk from $s$ terminates at $t$ and reflects the importance between $s$ and $t$ in a bidirectional way. As a generalization of Google's celebrated PageRank centrality, PPR has been extensively studied and has found multifaceted applications in many fields, such as network analysis, graph mining, and graph machine learning. Despite numerous studies devoted to PPR over the decades, efficient computation of PPR remains a challenging problem, and there is a dearth of systematic summaries and comparisons of existing algorithms. In this paper, we recap several frequently used techniques for PPR computation and conduct a comprehensive survey of various recent PPR algorithms from an algorithmic perspective. We classify these approaches based on the types of queries they address and review their methodologies and contributions. We also discuss some representative algorithms for computing PPR on dynamic graphs and in parallel or distributed environments.

cs.DS↗