Papers by Jiayi Yao

12 papers
LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Copied to clipboard

Challenge: Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach: They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome: The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.
InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach: They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome: The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Copied to clipboard

Challenge: Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach: They propose a method that conducts customized evaluation tailored to each target model.
Outcome: The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.
AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in machine translation (MT) have focused on scaling multilingual machine translation models and evaluation data to hundreds of languages, including multiple under-resourced languages.
Approach: They propose to use n-gram matching metrics to measure progress in multilingual machine translation to 13 typologically diverse African languages to create high-quality human evaluation data with simplified MQM guidelines.
Outcome: The proposed metrics have a higher correlation with human judgments than n-gram matching metrics such as BLEU and METEOR.
Reframing Responsibility: Framing-Aware Event Causality Identification (2026.acl-long)

Copied to clipboard

Challenge: Causal explanations in political narratives are often framed and contested.
Approach: They propose a framing-aware extension of ECI that models causal explanations as structured claims including responsibility targets, evaluative frams, source type, and epistemic modality.
Outcome: The proposed model enables quantitative analysis of divergent causal attribution across narratives.
Multilingual Language Model Pretraining using Machine-translated Data (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for collecting and filtering multilingual web data lead to most languages lagging behind English performance due to the Internet's English-centric nature.
Approach: They propose to translate a high-quality English web corpus into nine languages and pretrain a 1.3B-parameter model on it.
Outcome: The proposed model matches or outperforms multilingual LLMs of similar size across Non-English understanding and reasoning tasks despite being trained on an order of magnitude less data.
Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Copied to clipboard

Challenge: Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach: They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome: The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach: They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome: The proposed framework outperforms open-source baselines and is competitive with GPT-5.
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Copied to clipboard

Challenge: Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach: They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome: The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.
MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)

Copied to clipboard

Challenge: Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations.
Approach: They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency.
Outcome: The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types.
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach: They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome: The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.
Strings from the Library of Babel: Random Sampling as a Strong Baseline for Prompt Optimisation (2024.naacl-long)

Copied to clipboard

Challenge: Recent prompt optimisation approaches use the generative nature of language models to produce prompts, even rivaling the performance of human-curated prompts.
Approach: They propose to randomly sample tokens from the model vocabulary as "separators" they show that random separators are competitive baselines, having less than a 1% difference compared to previous self-optimisation methods.
Outcome: The proposed method outperforms human-curated prompts in nine text classification tasks and eight language models and has a 40% chance of performing better than human-generated separators.

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