Author name cluster

Xiaochi Wei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

AAAI Conference 2026 Conference Paper

Efficient Thought Space Exploration Through Strategic Intervention

Ziheng Li
Hengyi Cai
Xiaochi Wei
Yuchen Li
Shuaiqiang Wang
Zhi-Hong Deng
Dawei Yin

While large language models (LLMs) demonstrate emerging reasoning capabilities, current inference-time expansion methods incur prohibitive computational costs through exhaustive sampling. Through analyzing decoding trajectories, we observe that most next-token predictions align well with the golden output, except for a few critical tokens that lead to deviations. Inspired by this phenomenon, we propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components: 1) a hinter (powerful LLM) that provides probabilistic guidance at critical decision points, and 2) a practitioner (efficient smaller model) that executes major reasoning steps. The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), a theoretically-grounded metric that dynamically identifies intervention points by quantifying the divergence between practitioner's reasoning trajectory and hinter's expected distribution in a tree-structured probabilistic space. Through iterative tree updates guided by DIR, HPR reweights promising reasoning paths while deprioritizing low-probability branches. Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs: it achieves comparable performance to self-consistency and MCTS baselines while decoding only 1/5 tokens, and outperforms existing methods by at most 5.1% absolute accuracy while maintaining similar or lower FLOPs.

PDF Details DOI

ICLR Conference 2025 Conference Paper

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

Changle Qu
Sunhao Dai
Xiaochi Wei
Hengyi Cai
Shuaiqiang Wang
Dawei Yin 0001
Jun Xu 0001
Ji-Rong Wen

Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool documentation plays a crucial role by providing usage instructions for LLMs, thereby facilitating effective tool utilization. This paper concentrates on the critical challenge of bridging the comprehension gap between LLMs and external tools due to the inadequacies and inaccuracies inherent in existing human-centric tool documentation. We propose a novel framework, DRAFT, aimed at Dynamically Refining tool documentation through the Analysis of Feedback and Trials emanating from LLMs' interactions with external tools. This methodology pivots on an innovative trial-and-error approach, consisting of three distinct learning phases: experience gathering, learning from experience, and documentation rewriting, to iteratively enhance the tool documentation. This process is further optimized by implementing a diversity-promoting exploration strategy to ensure explorative diversity and a tool-adaptive termination mechanism to prevent overfitting while enhancing efficiency. Extensive experiments on multiple datasets demonstrate that DRAFT's iterative, feedback-based refinement significantly ameliorates documentation quality, fostering a deeper comprehension and more effective utilization of tools by LLMs. Notably, our analysis reveals that the tool documentation refined via our approach demonstrates robust cross-model generalization capabilities.

Details

TIST Journal 2020 Journal Article

A Discriminative Convolutional Neural Network with Context-aware Attention

Yuxiang Zhou
Lejian Liao
Yang Gao
Heyan Huang
Xiaochi Wei

Feature representation and feature extraction are two crucial procedures in text mining. Convolutional Neural Networks (CNN) have shown overwhelming success for text-mining tasks, since they are capable of efficiently extracting n -gram features from source data. However, vanilla CNN has its own weaknesses on feature representation and feature extraction. A certain amount of filters in CNN are inevitably duplicate and thus hinder to discriminatively represent a given text. In addition, most existing CNN models extract features in a fixed way (i.e., max pooling) that either limit the CNN to local optimum nor without considering the relation between all features, thereby unable to learn a contextual n -gram features adaptively. In this article, we propose a discriminative CNN with context-aware attention to solve the challenges of vanilla CNN. Specifically, our model mainly encourages discrimination across different filters via maximizing their earth mover distances and estimates the salience of feature candidates by considering the relation between context features. We validate carefully our findings against baselines on five benchmark datasets of classification and two datasets of summarization. The results of the experiments verify the competitive performance of our proposed model.

Details DOI

AAAI Conference 2019 Conference Paper

Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding

Changsen Yuan
Heyan Huang
Chong Feng
Xiao Liu
Xiaochi Wei

Distant supervision for relation extraction is an efficient method to reduce labor costs and has been widely used to seek novel relational facts in large corpora, which can be identified as a multi-instance multi-label problem. However, existing distant supervision methods suffer from selecting important words in the sentence and extracting valid sentences in the bag. Towards this end, we propose a novel approach to address these problems in this paper. Firstly, we propose a linear attenuation simulation to reflect the importance of words in the sentence with respect to the distances between entities and words. Secondly, we propose a non-independent and identically distributed (non-IID) relevance embedding to capture the relevance of sentences in the bag. Our method can not only capture complex information of words about hidden relations, but also express the mutual information of instances in the bag. Extensive experiments on a benchmark dataset have well-validated the effectiveness of the proposed method.

PDF Details

IJCAI Conference 2018 Conference Paper

Quality Matters: Assessing cQA Pair Quality via Transductive Multi-View Learning

Xiaochi Wei
Heyan Huang
Liqiang Nie
Fuli Feng
Richang Hong
Tat-Seng Chua

Community-based question answering (cQA) sites have become important knowledge sharing platforms, as massive cQA pairs are archived, but the uneven quality of cQA pairs leaves information seekers unsatisfied. Various efforts have been dedicated to predicting the quality of cQA contents. Most of them concatenate different features into single vectors and then feed them into regression models. In fact, the quality of cQA pairs is influenced by different views, and the agreement among them is essential for quality assessment. Besides, the lacking of labeled data significantly hinders the quality prediction performance. Toward this end, we present a transductive multi-view learning model. It is designed to find a latent common space by unifying and preserving information from various views, including question, answer, QA relevance, asker, and answerer. Additionally, rich information in the unlabeled test cQA pairs are utilized via transductive learning to enhance the representation ability of the common space. Extensive experiments on real-world datasets have well-validated the proposed model.

PDF Details

IJCAI Conference 2015 Conference Paper

Cross-Domain Collaborative Filtering with Review Text

Xin Xin
Zhirun Liu
Chin-Yew Lin
Heyan Huang
Xiaochi Wei
Ping Guo

Most existing cross-domain recommendation algorithms focus on modeling ratings, while ignoring review texts. The review text, however, contains rich information, which can be utilized to alleviate data sparsity limitations, and interpret transfer patterns. In this paper, we investigate how to utilize the review text to improve cross-domain collaborative filtering models. The challenge lies in the existence of non-linear properties in some transfer patterns. Given this, we extend previous transfer learning models in collaborative filtering, from linear mapping functions to non-linear ones, and propose a cross-domain recommendation framework with the review text incorporated. Experimental verifications have demonstrated, for new users with sparse feedback, utilizing the review text obtains 10% improvement in the AUC metric, and the nonlinear method outperforms the linear ones by 4%.

PDF Details

IJCAI Conference 2015 Conference Paper

Re-Ranking Voting-Based Answers by Discarding User Behavior Biases

Xiaochi Wei
Heyan Huang
Chin-Yew Lin
Xin Xin
Xianling Mao
Shangguang Wang

The vote mechanism is widely utilized to rank answers in community-based question answering sites. In generating a vote, a user’s attention is influenced by the answer position and appearance, in addition to real answer quality. Previously, these biases are ignored. As a result, the top answers obtained from this mechanism are not reliable, if the number of votes for the active question is not sufficient. In this paper, we solve this problem by analyzing two kinds of biases; position bias and appearance bias. We identify the existence of these biases and propose a joint click model for dealing with both of them. Our experiments in real data demonstrate how the ranking performance of the proposed model outperforms traditional methods with biases ignored by 15. 1% in precision@1, and 11. 7% in the mean reciprocal rank. A case st-udy on a manually labeled dataset futher supports the effectiveness of the proposed model.

PDF Details