Papers by Jun Yao

30 papers
Regret-Now: A Physics-Inspired Regret Framework for Temporal Knowledge Graph Question Answering with LLMs (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models have impressive results in general reasoning tasks, but they still exhibit a lack of dynamic error-correction.
Approach: They propose a temporal reasoning framework that uses the principle of minimum potential energy to model the reasoning process as a dynamic trajectory moving toward a more stable state.
Outcome: The proposed framework shows consistent gains over strong baselines on two standard TKGQA benchmarks.
Exploring Union and Intersection of Visual Regions for Generating Questions, Answers, and Distractors (2024.emnlp-main)

Copied to clipboard

Challenge: Existing efforts to generate image-related questions, correct answers, or challenge distractors are limited.
Approach: They propose to put the spotlight on different image regions to diversify QADs . they propose a framework that generates each QAD based on a recurrent multimodal encoder .
Outcome: The proposed framework puts the spotlight on different image regions to diversify QADs.
Generate-on-Graph: Treat LLM as both Agent and KG for Incomplete Knowledge Graph Question Answering (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to integrate LLMs with Knowledge Graphs (KGs) however, these methods are often incomplete to cover all the knowledge required to answer questions.
Approach: They propose to integrate LLMs with Knowledge Graphs (KGs) to address insufficient knowledge and hallucination issues in Large Language Models.
Outcome: The proposed method outperforms existing methods on two datasets.
Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)

Copied to clipboard

Challenge: Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time.
Approach: They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts .
Outcome: The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines.
Query2Triple: Unified Query Encoding for Answering Diverse Complex Queries over Knowledge Graphs (2023.findings-emnlp)

Copied to clipboard

Challenge: Complex Query Answering (CQA) is a challenge task of Knowledge Graphs due to incompleteness of KGs.
Approach: They propose a query embedding approach that decouples the training for simple and complex queries.
Outcome: The proposed approach decouples training for simple and complex queries and achieves state-of-the-art performance over three public benchmarks.
OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks focus on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation.
Approach: They propose a benchmarking tool that compares 1,000 curated optimization problems across three difficulty levels.
Outcome: The proposed model improves performance on hard problems while maintaining 27% accuracy.
R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Copied to clipboard

Challenge: Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach: They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome: The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.
Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension (2022.acl-long)

Copied to clipboard

Challenge: Procedural Multimodal Documents organize textual instructions and corresponding images step by step.
Approach: They propose a novel temporal-modal entity Graph for comprehending PMDs . they propose encoding and reasoning modules to capture textual and visual entities .
Outcome: The proposed model can capture textual and visual entities and trace their temporal-modal evolution.
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach: They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome: The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .
DisCal: Distribution-Aware Calibration for Mathematical Reasoning Under Character-Level Noisy Inputs (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for calibration of large reasoning models (LRMs) focus on clean inputs, leaving noise unexplored.
Approach: They propose a confidence calibration framework for character-level noisy inputs that extracts uncertainty signals from both the empirical answer distribution and the model’s predictive distribution and integrates them via a learned calibrator.
Outcome: Experiments on multiple mathematical reasoning benchmarks show that DisCal outperforms existing calibration methods under noisy inputs, reducing expected calibration error (ECE) by up to 39.21% and improving Area Under the Receiver Operating Characteristic Curve (AUROC) by 31.44%.
ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)

Copied to clipboard

Challenge: Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics.
Approach: They propose a method that integrates models, data, and tasks to refine datasets.
Outcome: The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains.
Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition (2026.acl-long)

Copied to clipboard

Challenge: Severe acoustic degradation results in unreliable ASR outputs . et al., 2024b): critical concerns regarding reliability and fairness of ASR .
Approach: They propose a multimodal framework that reframes ASR as semantics-guided speech reconstruction.
Outcome: The proposed framework achieves an average reduction in WER while also attaining 98.71% BERTScore and 96.7% USE over advanced baselines.
IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact (2024.findings-acl)

Copied to clipboard

Challenge: Existing quantization methods are compromising performance of large language models (LLMs) despite their high computational intensity, LLMs are still demanding intensive computation.
Approach: They propose to generate the KV cache of pivot tokens losslessly from the full-precision model.
Outcome: The proposed method generates the KV cache of pivot tokens losslessly from the full-precision model with no extra inference overhead.
LLaSA: Large Language and Structured Data Assistant (2025.naacl-long)

Copied to clipboard

Challenge: Structured knowledge grounding (SKG) tasks are a key part of many NLP applications.
Approach: They propose a framework for enhancing LLMs' ability to handle structured data . they represent various types of structured data in a unified hypergraph format .
Outcome: The proposed framework outperforms existing methods on SKG tasks using LoRA finetuning.
Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering (2025.coling-main)

Copied to clipboard

Challenge: Recent studies indicate that Large Language Models model rich knowledge, but it is often not activated and awakened.
Approach: They propose a framework that leverages richer context to enhance question answering . Explicit awakening fine-tunes a context generator to create a synthetic, compressed document that functions as symbolic context.
Outcome: The proposed framework mimics the human ability to answer questions using only thinking and recalling to compensate for knowledge gaps.
Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method (D18-1)

Copied to clipboard

Challenge: Experimental results show that Sequence-to-sequence models tend to generate generic/dull responses .
Approach: They propose a statistical re-weighting method that assigns different weights for multiple responses of the same query.
Outcome: The proposed method improves acceptance rate of generated responses and significantly reduces generated generic responses.
MSIA: Adaptive Medical Multimodal Multi-turn Semantic Jailbreak (2026.findings-acl)

Copied to clipboard

Challenge: Medical large language models exhibit high domain specificity and condensed semantics, making them vulnerable to diagnostic errors in real-world clinical settings.
Approach: They propose a framework for modeling and inducing multi-turn medical semantic jailbreaks in clinical dialogues.
Outcome: Experiments on chest X-ray-based multimodal medical dialogues show that MSIA outperforms existing jailbreak methods with an average success rate of 76.67%.
Unsupervised Preference-Aware Language Identification (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies do not consider inter-personal variations due to the lack of user annotated training data.
Approach: They propose to use user preferences to identify ambiguous texts in multilingual applications without user annotated training data to build a preference-aware LID model.
Outcome: The proposed model significantly outperforms existing LID systems on handling ambiguous texts.
UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) scaling is limited by data quality and domain mixing and instance selection are two separate problems.
Approach: They propose a framework that unifies mixing and selection without training proxy models or relying on external reference datasets.
Outcome: The proposed framework achieves 2.0 data efficiency over a random baseline and further improves overall performance compared to SOTA methods in reasoning-heavy evaluations and multilingual generalization.
Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions (2025.findings-acl)

Copied to clipboard

Challenge: Existing video QADs are generated using video captions, incurring significant costs and resulting in bias.
Approach: They propose to use temporal motion to describe video objects to generate diverse QADs focusing on different objects and interactions.
Outcome: The proposed approach improves consistency and diversity of generated QADs on the NExT-QA and Perception Test benchmarks.
M-TRACE: Detecting and Mitigating Time-Anchor Drift via Step-wise Conflict Checking in Temporal Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Experimental results show that M-TRACE effectively reduces time-anchor drift . external knowledge may be inaccurate while internal knowledge can become outdated .
Approach: They propose a multi-agent reasoning framework for temporal knowledge conflicts . they propose 'TimeConfQA' which guides conflict-aware final reasoning .
Outcome: Experimental results show that M-TRACE reduces time-anchor drift and improves performance on complex temporal question answering tasks.
Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue (2023.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge selection methods are costly to learn and difficult to interpret when errors arise in the generated responses.
Approach: They propose a generator-agnostic knowledge selection method to select context-related knowledge among different knowledge structures and variable knowledge requirements.
Outcome: The proposed method can select knowledge accurately in advance and reduce learning, adjustment, and interpretation burden of later models.
GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)

Copied to clipboard

Challenge: Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction.
Approach: They propose a series of datasets for training visual-based GUI agents using general VLMs.
Outcome: The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks.
MoDE-CoTD: Chain-of-Thought Distillation for Complex Reasoning Tasks with Mixture of Decoupled LoRA-Experts (2024.lrec-main)

Copied to clipboard

Challenge: Current Chain-of-thought Distillation methods hinder CoT reasoning performance . student models are separately distilled from specific reasoning tasks . parameter update of student models severely harms CoT ability on unseen reasoning tasks.
Approach: They propose a method which distills Chain-of-thought reasoning ability of large language models to much smaller student models.
Outcome: The proposed method improves the reasoning ability of large language models on 14 datasets.
Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing diverse NMT models lack translation diversity due to a discrepancy between training and inference . despite the success of diverse NTM, there is still a lack of translation diversity .
Approach: They propose a multi-candidate optimization framework for diverse NMT to deal with this defect.
Outcome: The proposed framework is transparent to basic diverse NMT models, and universally makes better trade-off between diversity and quality.
SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have many advantages but they also pose significant safety risks.
Approach: They propose a method to enhance the safety self-evaluation capability of LLMs . they perform semantic mutations on the original safety evaluation questions .
Outcome: The proposed method improves safety self-evaluation accuracy by 5.86% and 7.79% over baseline methods on Chinese and English datasets.
Prediction and Calibration: Complex Reasoning over Knowledge Graph with Bi-directional Directed Acyclic Graph Neural Network (2023.findings-acl)

Copied to clipboard

Challenge: Knowledge graphs (KGs) organize world knowledge as interlinked triples which describe entities and their relationships.
Approach: They propose a bi-directional Directed Acyclic Graph neural network that splits the reasoning process into prediction and calibration.
Outcome: The proposed model outperforms previous QE models on FB15k, FB16k-237, and NELL995 on prediction and calibration.
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)

Copied to clipboard

Challenge: a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say .
Approach: They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible .
Outcome: The proposed framework achieves state-of-the-art performance among open-source projects.
Can We Learn Question, Answer, and Distractors All from an Image? A New Task for Multiple-choice Visual Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies focus on generating QADs from image and question, but a novel task is needed to generate meaningful questions, correct answers, and challenging distractors.
Approach: They propose a task to generate QADs from images and encode images together . they use contrastive learning to ensure consistency of QAD generated and tested .
Outcome: Empirical evaluations on the benchmark dataset validate the performance of the proposed task.
Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrieval (2025.findings-acl)

Copied to clipboard

Challenge: Existing approaches to multihop question answering (MHQA) over long contexts are often neglecting explicit reasoning or incurring expensive computational costs due to full-attention mechanisms over long contextuals.
Approach: They propose a framework that integrates Monte Carlo Tree Search (MCTS) with dynamic key-value retrieval to enable iterative, context-aware reasoning.
Outcome: The proposed framework integrates Monte Carlo Tree Search (MCTS) with dynamic key-value (KV) retrieval to enable iterative, context-aware reasoning.

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