arXiv subjects

Minghe Yu

Publications and source records attributed to Minghe Yu.

14 recordsLinked to original sources

arXiv2026

MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

Multi-hop question answering is a fundamental challenge in retrieval-augmented generation (RAG), because deriving an answer requires integrating dispersed evidence. Iterative RAG (iRAG) is widely used for this challenge, but existing methods have two limitations. First, most methods still support each reasoning step with single-granularity evidence, making it difficult to balance information density and contextual noise. Second, existing methods often answer the original question only after aggregating evidence retrieved across intermediate steps, so redundant evidence and intermediate retrieval errors may accumulate and degrade the final answer. To address these limitations, we propose MEGRAG, an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph. Offline, MEGRAG links passages to their sentences and extracted triples through a cross-granularity index. Online, it retrieves passages for the current query and selects aligned evidence, starting with compact triples and adding sentence or passage context as needed. MEGRAG uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved. If not, it identifies the missing information and formulates a focused next query; otherwise, it stops retrieval and returns the answer. Extensive experiments demonstrate consistent gains over a diverse set of RAG baselines.

cs.AI↗

arXiv2026

Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval

Retrieval-Augmented Generation (RAG) has become a dominant paradigm for mitigating hallucinations in Large Language Models (LLMs) by incorporating external knowledge. However, existing RAG systems often struggle to effectively integrate and reason over key evidence scattered across noisy retrieved documents, particularly in multi-hop scenarios. In this paper, we propose KAIR, a Knowledge Anchoring framework for Iterative Retrieval that anchors knowledge within retrieved knowledge to guide LLMs to locate the key information. During iterative retrieval, KAIR progressively updates the knowledge index to anchor salient evidence from retrieved documents. The evolving index serves as a navigational anchoring index that enables the LLM to assess knowledge sufficiency and formulate subsequent retrieval queries. Finally, KAIR generates answers by jointly leveraging the retrieved documents and the finalized anchoring index. Experiments on four multi-hop question answering benchmarks demonstrate that KAIR consistently outperforms strong RAG baselines. Further analysis shows that KAIR effectively anchors key knowledge and alleviates the context noise during iterative retrieval, improving the LLM's ability to associate and reason over dispersed evidence across retrieved documents. All code and data are available at https://github.com/NEUIR/KAIR.

cs.CL↗

arXiv2025

MSC-180: A Benchmark for Automated Formal Theorem Proving from Mathematical Subject Classification

Automated Theorem Proving (ATP) represents a core research direction in artificial intelligence for achieving formal reasoning and verification, playing a significant role in advancing machine intelligence. However, current large language model (LLM)-based theorem provers suffer from limitations such as restricted domain coverage and weak generalization in mathematical reasoning. To address these issues, we propose MSC-180, a benchmark for evaluation based on the MSC2020 mathematical subject classification. It comprises 180 formal verification problems, 3 advanced problems from each of 60 mathematical branches, spanning from undergraduate to graduate levels. Each problem has undergone multiple rounds of verification and refinement by domain experts to ensure formal accuracy. Evaluations of state-of-the-art LLM-based theorem provers under the pass@32 setting reveal that the best model achieves only an 18.89% overall pass rate, with prominent issues including significant domain bias (maximum domain coverage 41.7%) and a difficulty gap (significantly lower pass rates on graduate-level problems). To further quantify performance variability across mathematical domains, we introduce the coefficient of variation (CV) as an evaluation metric. The observed CV values are 4-6 times higher than the statistical high-variability threshold, indicating that the models still rely on pattern matching from training corpora rather than possessing transferable reasoning mechanisms and systematic generalization capabilities. MSC-180, together with its multi-dimensional evaluation framework, provides a discriminative and systematic benchmark for driving the development of next-generation AI systems with genuine mathematical reasoning abilities.

cs.AI↗

arXiv2025

Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling

Large Language Models (LLMs) as automatic evaluators, commonly referred to as LLM-as-a-Judge, have also attracted growing attention. This approach plays a vital role in aligning LLMs with human judgments, providing accurate and reliable assessments. However, LLM-based judgment models often exhibit judgment preference bias during the evaluation phase, tending to favor responses generated by themselves, undermining the reliability of their judgments. This paper introduces the Group-Based Polling Optimization (Genii), an unsupervised multi-agent collaborative optimization framework that mitigates the inherent judgment preference bias of judgment models. Specifically, Genii integrates various LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism to optimize each client agent unsupervisedly. Our experiments demonstrate that Genii outperforms supervised models trained on annotated judgment data, while requiring no human-labeled annotations. Genii consistently improves performance across different client agents during the polling, even when weaker models act as server agents. Further analysis reveals that Genii effectively mitigates judgment preference bias of LLM-based judgment models, demonstrating its effectiveness. All codes are available at https://github.com/NEUIR/Genii.

cs.CL↗

arXiv2025

Advancing Knowledge Tracing by Exploring Follow-up Performance Trends

Intelligent Tutoring Systems (ITS), such as Massive Open Online Courses, offer new opportunities for human learning. At the core of such systems, knowledge tracing (KT) predicts students' future performance by analyzing their historical learning activities, enabling an accurate evaluation of students' knowledge states over time. We show that existing KT methods often encounter correlation conflicts when analyzing the relationships between historical learning sequences and future performance. To address such conflicts, we propose to extract so-called Follow-up Performance Trends (FPTs) from historical ITS data and to incorporate them into KT. We propose a method called Forward-Looking Knowledge Tracing (FINER) that combines historical learning sequences with FPTs to enhance student performance prediction accuracy. FINER constructs learning patterns that facilitate the retrieval of FPTs from historical ITS data in linear time; FINER includes a novel similarity-aware attention mechanism that aggregates FPTs based on both frequency and contextual similarity; and FINER offers means of combining FPTs and historical learning sequences to enable more accurate prediction of student future performance. Experiments on six real-world datasets show that FINER can outperform ten state-of-the-art KT methods, increasing accuracy by 8.74% to 84.85%.

cs.CY↗

arXiv2025

Automated Formalization via Conceptual Retrieval-Augmented LLMs

Interactive theorem provers (ITPs) require manual formalization, which is labor-intensive and demands expert knowledge. While automated formalization offers a potential solution, it faces two major challenges: model hallucination (e.g., undefined predicates, symbol misuse, and version incompatibility) and the semantic gap caused by ambiguous or missing premises in natural language descriptions. To address these issues, we propose CRAMF, a Concept-driven Retrieval-Augmented Mathematical Formalization framework. CRAMF enhances LLM-based autoformalization by retrieving formal definitions of core mathematical concepts, providing contextual grounding during code generation. However, applying retrieval-augmented generation (RAG) in this setting is non-trivial due to the lack of structured knowledge bases, the polymorphic nature of mathematical concepts, and the high precision required in formal retrieval. We introduce a framework for automatically constructing a concept-definition knowledge base from Mathlib4, the standard mathematical library for the Lean 4 theorem prover, indexing over 26,000 formal definitions and 1,000+ core mathematical concepts. To address conceptual polymorphism, we propose contextual query augmentation with domain- and application-level signals. In addition, we design a dual-channel hybrid retrieval strategy with reranking to ensure accurate and relevant definition retrieval. Experiments on miniF2F, ProofNet, and our newly proposed AdvancedMath benchmark show that CRAMF can be seamlessly integrated into LLM-based autoformalizers, yielding consistent improvements in translation accuracy, achieving up to 62.1% and an average of 29.9% relative improvement.

cs.AI↗

arXiv2025

Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation

Multimodal Retrieval-Augmented Generation (MRAG) has shown promise in mitigating hallucinations in Multimodal Large Language Models (MLLMs) by incorporating external knowledge. However, existing methods typically adhere to rigid retrieval paradigms by mimicking fixed retrieval trajectories and thus fail to fully exploit the knowledge of different retrieval experts through dynamic interaction based on the model's knowledge needs or evolving reasoning states. To overcome this limitation, we introduce Mixture-of-Retrieval Experts (MoRE), a novel framework that enables MLLMs to collaboratively interact with diverse retrieval experts for more effective knowledge exploitation. Specifically, MoRE learns to dynamically determine which expert to engage with, conditioned on the evolving reasoning state. To effectively train this capability, we propose Stepwise Group Relative Policy Optimization (Step-GRPO), which goes beyond sparse outcome-based supervision by encouraging MLLMs to interact with multiple retrieval experts and synthesize fine-grained rewards, thereby teaching the MLLM to fully coordinate all experts when answering a given query. Experimental results on diverse open-domain QA benchmarks demonstrate the effectiveness of MoRE, achieving average performance gains of over 7% compared to competitive baselines. Notably, MoRE exhibits strong adaptability by dynamically coordinating heterogeneous experts to precisely locate relevant information, validating its capability for robust, reasoning-driven expert collaboration. All codes and data are released on https://github.com/OpenBMB/MoRE.

cs.CL↗

arXiv2025

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection

Large Language Models (LLMs) have exhibited strong reasoning capabilities and achieved remarkable performance in mathematical problem-solving tasks. Recently, distilling reasoning ability from long-form Chains-of-Thought (CoTs) has emerged as a promising approach for enhancing Small Language Models (SLMs). Existing studies typically treat SLMs as student models and use long-form CoTs as supervision signals for Supervised Fine-Tuning (SFT) to transfer reasoning ability. However, such long-form CoT teachers are usually unaware of the student model's capacity, which limits the effective utilization of the provided reasoning traces. To overcome this limitation, we propose errOr-aware self-ReflectION (ORION), a framework that refines teacher CoTs through an Error-Aware Reflection process. ORION enables the student model to construct more tailored teacher CoTs by refining teacher CoTs and incorporating its own reasoning errors. Experiments on multiple mathematical reasoning benchmarks demonstrate that ORION consistently improves performance by more than 2% over all baselines. Further analysis reveals that the CoTs constructed by ORION exhibit higher coherence and logical consistency, thereby serving as more effective supervision signals for SFT. All codes are available at https://github.com/NEUIR/ORION.git.

cs.CL↗

arXiv2024

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human debugging typically follows a multi-stage process, which includes Bug Localization, Bug Identification, Code Repair, and Code Recognition. However, existing code debugging benchmarks predominantly focus on the Code Repair stage, which offers only a limited perspective on evaluating the debugging capabilities of LLMs. In this paper, we introduce DEBUGEVAL, a comprehensive benchmark for evaluating the debugging abilities of LLMs by emulating the multi-stage human debugging process. Through evaluating on DEBUGEVAL, we observe that 7B-scale models consistently underperform compared to their larger counterparts, highlighting their limitations in comprehending code semantics. In this case, we propose the COmmunicative Agent-based data SynThesis (COAST) framework, which employs a multi-agent system to generate high-quality training data for supervised fine-tuning (SFT). Experimental results demonstrate that COAST-generated data outperform human-curated and GPT-4-generated data, enabling 7B-scale LLMs to achieve debugging performance comparable to GPT-3.5. All data and codes are available at https://github.com/NEUIR/COAST.

cs.SE↗

arXiv2023

Interpretable Knowledge Tracing via Response Influence-based Counterfactual Reasoning

Knowledge tracing (KT) plays a crucial role in computer-aided education and intelligent tutoring systems, aiming to assess students' knowledge proficiency by predicting their future performance on new questions based on their past response records. While existing deep learning knowledge tracing (DLKT) methods have significantly improved prediction accuracy and achieved state-of-the-art results, they often suffer from a lack of interpretability. To address this limitation, current approaches have explored incorporating psychological influences to achieve more explainable predictions, but they tend to overlook the potential influences of historical responses. In fact, understanding how models make predictions based on response influences can enhance the transparency and trustworthiness of the knowledge tracing process, presenting an opportunity for a new paradigm of interpretable KT. However, measuring unobservable response influences is challenging. In this paper, we resort to counterfactual reasoning that intervenes in each response to answer \textit{what if a student had answered a question incorrectly that he/she actually answered correctly, and vice versa}. Based on this, we propose RCKT, a novel response influence-based counterfactual knowledge tracing framework. RCKT generates response influences by comparing prediction outcomes from factual sequences and constructed counterfactual sequences after interventions. Additionally, we introduce maximization and inference techniques to leverage accumulated influences from different past responses, further improving the model's performance and credibility. Extensive experimental results demonstrate that our RCKT method outperforms state-of-the-art knowledge tracing methods on four datasets against six baselines, and provides credible interpretations of response influences.

cs.CY↗

arXiv2023

A Probabilistic Generative Model for Tracking Multi-Knowledge Concept Mastery Probability

Knowledge tracing aims to track students' knowledge status over time to predict students' future performance accurately. Markov chain-based knowledge tracking (MCKT) models can track knowledge concept mastery probability over time. However, as the number of tracked knowledge concepts increases, the time complexity of MCKT predicting student performance increases exponentially (also called explaining away problem. In addition, the existing MCKT models only consider the relationship between students' knowledge status and problems when modeling students' responses but ignore the relationship between knowledge concepts in the same problem. To address these challenges, we propose an inTerpretable pRobAbilistiC gEnerative moDel (TRACED), which can track students' numerous knowledge concepts mastery probabilities over time. To solve \emph{explain away problem}, we design Long and Short-Term Memory (LSTM)-based networks to approximate the posterior distribution, predict students' future performance, and propose a heuristic algorithm to train LSTMs and probabilistic graphical model jointly. To better model students' exercise responses, we proposed a logarithmic linear model with three interactive strategies, which models students' exercise responses by considering the relationship among students' knowledge status, knowledge concept, and problems. We conduct experiments with four real-world datasets in three knowledge-driven tasks. The experimental results show that TRACED outperforms existing knowledge tracing methods in predicting students' future performance and can learn the relationship among students, knowledge concepts, and problems from students' exercise sequences. We also conduct several case studies. The case studies show that TRACED exhibits excellent interpretability and thus has the potential for personalized automatic feedback in the real-world educational environment.

cs.LG↗

arXiv2020

AIBench Training: Balanced Industry-Standard AI Training Benchmarking

Earlier-stage evaluations of a new AI architecture/system need affordable benchmarks. Only using a few AI component benchmarks like MLPerfalone in the other stages may lead to misleading conclusions. Moreover, the learning dynamics are not well understood, and the benchmarks' shelf-life is short. This paper proposes a balanced benchmarking methodology. We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent. After performing an exhaustive survey on Internet service AI domains, we identify and implement nineteen representative AI tasks with state-of-the-art models. For repeatable performance ranking (RPR subset) and workload characterization (WC subset), we keep two subsets to a minimum for affordability. We contribute by far the most comprehensive AI training benchmark suite. The evaluations show: (1) AIBench Training (v1.1) outperforms MLPerfTraining (v0.7) in terms of diversity and representativeness of model complexity, computational cost, convergent rate, computation, and memory access patterns, and hotspot functions; (2) Against the AIBench full benchmarks, its RPR subset shortens the benchmarking cost by 64%, while maintaining the primary workload characteristics; (3) The performance ranking shows the single-purpose AI accelerator like TPU with the optimized TensorFlowframework performs better than that of GPUs while losing the latter's general support for various AI models. The specification, source code, and performance numbers are available from the AIBench homepage https://www.benchcouncil.org/aibench-training/index.html.

cs.AI↗

arXiv2020

AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite

Domain-specific software and hardware co-design is encouraging as it is much easier to achieve efficiency for fewer tasks. Agile domain-specific benchmarking speeds up the process as it provides not only relevant design inputs but also relevant metrics, and tools. Unfortunately, modern workloads like Big data, AI, and Internet services dwarf the traditional one in terms of code size, deployment scale, and execution path, and hence raise serious benchmarking challenges. This paper proposes an agile domain-specific benchmarking methodology. Together with seventeen industry partners, we identify ten important end-to-end application scenarios, among which sixteen representative AI tasks are distilled as the AI component benchmarks. We propose the permutations of essential AI and non-AI component benchmarks as end-to-end benchmarks. An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application. We design and implement a highly extensible, configurable, and flexible benchmark framework, on the basis of which, we propose the guideline for building end-to-end benchmarks, and present the first end-to-end Internet service AI benchmark. The preliminary evaluation shows the value of our benchmark suite---AIBench against MLPerf and TailBench for hardware and software designers, micro-architectural researchers, and code developers. The specifications, source code, testbed, and results are publicly available from the web site \url{http://www.benchcouncil.org/AIBench/index.html}.

cs.PF↗

arXiv2019

AIBench: An Industry Standard Internet Service AI Benchmark Suite

Today's Internet Services are undergoing fundamental changes and shifting to an intelligent computing era where AI is widely employed to augment services. In this context, many innovative AI algorithms, systems, and architectures are proposed, and thus the importance of benchmarking and evaluating them rises. However, modern Internet services adopt a microservice-based architecture and consist of various modules. The diversity of these modules and complexity of execution paths, the massive scale and complex hierarchy of datacenter infrastructure, the confidential issues of data sets and workloads pose great challenges to benchmarking. In this paper, we present the first industry-standard Internet service AI benchmark suite---AIBench with seventeen industry partners, including several top Internet service providers. AIBench provides a highly extensible, configurable, and flexible benchmark framework that contains loosely coupled modules. We identify sixteen prominent AI problem domains like learning to rank, each of which forms an AI component benchmark, from three most important Internet service domains: search engine, social network, and e-commerce, which is by far the most comprehensive AI benchmarking effort. On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales. The specifications, source code, and performance numbers are publicly available from the benchmark council web site http://www.benchcouncil.org/AIBench/index.html.

cs.CV↗