BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Chao Jiang

Chao Jiang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computation and Languagecond-mat.stat-mechMachine Learningquant-phArtificial IntelligenceMethodologyphysics.ao-phphysics.data-an

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
7works
0followers
8topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

7 published item(s)

preprint2026arXiv

Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendation

We propose Compressed Video Aggregator (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning. It aggregates frozen VFM embeddings, and uses latent reasoning without cross-attention projection, producing compact video embeddings for recommenders. Due to the redundancy in the frame count of the original benchmark and its overly coarse sampling, we used titles to re-select key frames based on CLIP. Experiments on MicroLens and Short-Video show consistent gains with orders-of-magnitude reductions in training time and GPU memory, and re-selected frames can further enhance the performance of all methods, including CVA. Furthermore, we also discussed the impact of several scenarios involving erroneous titles on our method. Code will be released soon.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

KDCM: Reducing Hallucination in LLMs through Explicit Reasoning Structures

To mitigate hallucinations in large language models (LLMs), we propose a framework that focuses on errors induced by prompts. Our method extends a chain-style knowledge distillation approach by incorporating a programmable module that guides knowledge graph exploration. This module is embedded as executable code within the reasoning prompt, allowing the model to leverage external structured knowledge during inference. Based on this design, we develop an enhanced distillation-based reasoning framework that explicitly regulates intermediate reasoning steps, resulting in more reliable predictions. We evaluate the proposed approach on multiple public benchmarks using GPT-4 and LLaMA-3.3. Experimental results show that code-guided reasoning significantly improves contextual modeling and reduces prompt-induced hallucinations. Specifically, HIT@1, HIT@3, and HIT@5 increase by 15.64%, 13.38%, and 13.28%, respectively, with scores exceeding 95% across several evaluation settings. These findings indicate that the proposed method effectively constrains erroneous reasoning while improving both accuracy and interpretability.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning

To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code module to guide knowledge-graph exploration and incorporate code as part of the chain-of-thought prompt, forming an external knowledge input that provides more accurate and structured information to the model. Based on this design, we develop an improved knowledge distillation chain-style model and leverage it to analyze and constrain the reasoning process of LLMs, thereby improving inference accuracy. We empirically evaluate the proposed approach using GPT-4 and LLaMA-3.3 on multiple public datasets. Experimental results demonstrate that incorporating code modules significantly enhances the model's ability to capture contextual information and effectively mitigates prompt-induced hallucinations. Specifically, HIT@1, HIT@3, and HIT@5 improve by 15.64%, 13.38%, and 13.28%, respectively. Moreover, the proposed method achieves HIT@1, HIT@3, and HIT@5 scores exceeding 95% across several evaluation settings. These results indicate that the proposed approach substantially reduces hallucination behavior while improving the accuracy and verifiability of large language models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Application of simultaneous and continuous measurement of noncommutative observables: Preparation of the pure ideal quadrature-squeezed state by feedback control

As an application of the simultaneous and continuous measurement of noncommutative observables formulated in our previous paper [C. Jiang and G. Watanabe, Phys. Rev. A 102, 062216 (2020)], we propose a scheme to generate the pure ideal quadrature-squeezed state in a one-dimensional harmonic oscillator system by the feedback control based on such type of measurement of noncommutative quadrature observables. We find that, by appropriately setting the strengths of the measurement and the feedback control, the pure ideal quadrature-squeezed state with arbitrary squeezedness can be produced. This is in contrast to the scheme based on the single-observable measurement and the feedback control, where only nonideal squeezed states with squeezing of the measured quadrature are produced.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Densely connected neural networks for nonlinear regression

Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers and the original concatenation shortcuts are maintained to reuse the feature. To investigate the effects of depth and input dimension of proposed model, careful validations are performed by extensive numerical simulation. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Furthermore, compared with the baseline models including support vector regression, decision tree regression, and residual regression, our proposed model with the optimal depth performs best. Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation (0.91) with observations, which indicates that our model could advance environmental data analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Quantum dynamics under simultaneous and continuous measurement of noncommutative observables

We consider simultaneous and continuous measurement of two noncommutative observables of the system whose commutator is not necessarily a $c$-number. We revisit the Arthurs-Kelly model and generalize it to describe the simultaneous measurement of two observables of the system. Using this generalized model, we continuously measure the system by following the scheme proposed by Scott and Milburn [Scott and Milburn, Phys. Rev. A 63, 042101 (2001)]. We find that the unconditioned master equation reduces to the Lindblad form in the continuous limit. In addition, we find that the master equation does not contain a cross term of these two measurements. Finally, we propose a scheme to prepare the state of a two-level system in an external field by feedback control based on the simultaneous, continuous measurement of the two observables.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Discourse Level Factors for Sentence Deletion in Text Simplification

This paper presents a data-driven study focusing on analyzing and predicting sentence deletion -- a prevalent but understudied phenomenon in document simplification -- on a large English text simplification corpus. We inspect various document and discourse factors associated with sentence deletion, using a new manually annotated sentence alignment corpus we collected. We reveal that professional editors utilize different strategies to meet readability standards of elementary and middle schools. To predict whether a sentence will be deleted during simplification to a certain level, we harness automatically aligned data to train a classification model. Evaluated on our manually annotated data, our best models reached F1 scores of 65.2 and 59.7 for this task at the levels of elementary and middle school, respectively. We find that discourse level factors contribute to the challenging task of predicting sentence deletion for simplification.

0 citations0 reviewsNo code linkedOpen access