Papers by Yu Zhong

27 papers
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs (2026.acl-long)

Copied to clipboard

Challenge: High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context .
Approach: They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage.
Outcome: The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora.
MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026.acl-long)

Copied to clipboard

Challenge: Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach: They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome: The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)

Copied to clipboard

Challenge: Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations .
Approach: They propose a framework to synthesize complex charts and reliable reasoning data from scratch.
Outcome: Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models .
Social Biases in NLP Models as Barriers for Persons with Disabilities (2020.acl-main)

Copied to clipboard

Challenge: toxicity prediction and sentiment analysis models perpetuate undesirable social biases from the data on which they are trained.
Approach: They propose to use toxicity prediction and sentiment analysis to examine whether NLP models perpetuate undesirable biases towards mentions of disability.
Outcome: The proposed models contain undesirable biases towards mentions of disability in two English language models.
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values.
Approach: They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though.
Outcome: The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets.
Semantic Evaluation for Text-to-SQL with Distilled Test Suites (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods to evaluate semantic accuracy of Text-to-SQL models are not accurate.
Approach: They propose a test suite accuracy method to approximate semantic accuracy for Text-to-SQL models.
Outcome: The proposed method evaluates 21 models submitted to the Spider leader board and manually checks on 100 examples.
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Copied to clipboard

Challenge: Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach: They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome: The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow (2026.findings-acl)

Copied to clipboard

Challenge: Autoregressive (AR) language models dominate modern natural language processing due to strong likelihood-based training objectives and reliable left-to-right decoding.
Approach: They characterize MDLM behavior along two dimensions: parallelism strength and generation order . authors propose a Generate-then-Edit paradigm that mitigates dependency loss .
Outcome: The proposed model improves on tasks that require "backward information" the Generate-then-Edit paradigm improves parallel decoding efficiency while reducing dependency loss.
AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving (2025.findings-emnlp)

Copied to clipboard

Challenge: Vision-Language Models struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning.
Approach: AgentThink integrates Chain-of-Thought reasoning with dynamic, agent-style tool invocation for autonomous driving tasks.
Outcome: Experiments on the DriveLMM-o1 benchmark show AgentThink significantly boosts overall reasoning scores by 53.91% and enhances answer accuracy by 33.54% .
LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach: This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome: The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.
ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks (2025.acl-long)

Copied to clipboard

Challenge: Recent studies show that obfuscation techniques for MLaaS are susceptible to embedding inversion attacks (EIAs).
Approach: They propose a model obfuscation framework that protects client inputs from embedding inversion attacks by obliviously obbing models.
Outcome: The proposed framework outperforms existing works in utility by 10% with a nearly 80% resistance rate against embedding inversion attacks.
Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation (2024.findings-emnlp)

Copied to clipboard

Challenge: Speculative decoding is a novel method to expedite inference in autoregressive (large) language models.
Approach: They propose to use a smaller model as a draft model to speculate a block of tokens, which the target model then evaluates for acceptance.
Outcome: The proposed method can be used to accelerate inference in autoregressive (large) language models by using smaller models as draft models to speculate tokens for multiple inference steps.
MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs (2020.acl-main)

Copied to clipboard

Challenge: Massive open online courses (MOOCs) are a popular educational platform for advanced research.
Approach: They propose to use MOOCCube to build a large-scale data repository of over 700 MOOC courses, 100k concepts, 8 million student behaviors with an external resource.
Outcome: The proposed datasets show that they can facilitate research in MOOCs.
Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to enhancing large language models fail to emphasize specific constraints and unlock the underlying knowledge.
Approach: They propose a method that emphasizes specific constraints and unlocks knowledge within LLMs by iteratively emphasising on specific constraints.
Outcome: The proposed method outperforms existing methods in enhancing generated content, especially in terms of specificity.
AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor.
Approach: They propose a reward-based generalizable reward model to guide the policy model for effective test-time search.
Outcome: The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average.
TVWorld: Foundations for Remote-Control TV Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on large vision–language models focuses on point-and-click interaction, while remote-control interaction is underexplored.
Approach: They propose a topology-aware training framework that injects topology awareness into LVLMs.
Outcome: The proposed model achieves 68.3% success rate on TVWorld-N, surpassing closed-source benchmarks and state-of-the-art (SOTA) benchmarks show that existing agents lack topology awareness for focus-based, long-horizon TV navigation.
Causal-Debias: Unifying Debiasing in Pretrained Language Models and Fine-tuning via Causal Invariant Learning (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to remove unwanted stereotypical associations from pretrained language models (PLMs) are often focused on removing unwanted stereotypes from PLMs.
Approach: They propose a framework to remove unwanted stereotypical associations in pretrained language models . they propose bias-relevant factors are causal, while labelrelevant factors causal .
Outcome: The proposed framework reduces stereotypical associations after PLMs are fine-tuned . the proposed framework mitigates bias from a causal invariant perspective .
QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization (2021.naacl-main)

Copied to clipboard

Challenge: Existing work on meeting summarization tasks is limited to short summaries that cover all the content of a meeting.
Approach: They propose a query-based multi-domain meeting summarization task that generates a single short summary of meetings based on a transcript.
Outcome: The proposed task is based on 1,808 query-summary pairs over 232 meetings in multiple domains.
Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge.
Approach: They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage.
Outcome: The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold.
LOCR: Location-Guided Transformer for Optical Character Recognition (2024.findings-emnlp)

Copied to clipboard

Challenge: Academic documents are packed with texts, equations, tables, and figures, posing challenges for accurate OCR results.
Approach: They propose a model that integrates location guiding into the transformer architecture during autoregression.
Outcome: The proposed model outperforms existing methods on an original large-scale dataset comprising 53M text-location pairs from 89K academic document pages.
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately .
Approach: They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes .
Outcome: The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show .
Inter-sentence Context Modeling and Structure-aware Representation Enhancement for Conversational Sentiment Quadruple Extraction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies struggle to capture complete dialogue semantics due to inadequate inter-utterance modeling and the underutilization of dialogue structure.
Approach: They propose a model to extract dialogue aspect sentiment quadruples from dialogues using a sentence-by-sentence encoding module.
Outcome: The proposed model extracts quadruples of target-aspect-opinion-sentiment from dialogues.
T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Copied to clipboard

Challenge: Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach: They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome: The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach: They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome: The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .
Learning Fine-Grained Grounded Citations for Attributed Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: despite impressive performance, large language models still struggle with hallucinations . current approaches suffer from suboptimal citation quality due to reliance on in-context learning .
Approach: They propose a framework that teaches large language models to generate fine-grained citations.
Outcome: The proposed framework outperforms all baselines on the ALCE benchmark and achieves an average improvement of 14.21% in citation quality.
A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Copied to clipboard

Challenge: Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach: They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome: The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach: They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome: The proposed system outperforms baselines in the open domain task-solving benchmark.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations