Papers by Peng Qiu

22 papers
Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language Models (2025.acl-long)

Copied to clipboard

Challenge: composition of pre-training datasets for large language models remains undisclosed . current methods for evaluating data quality are limited by single-dimensional evaluation or redundancy-focused strategies.
Approach: They propose a multi-dimensional data selection method that integrates dimensions with existing quality metrics through learned optimal weightings.
Outcome: The proposed method doubles convergence speed for 1.3B model models and improves downstream task performance by 3.23%.
SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues (2021.acl-long)

Copied to clipboard

Challenge: Existing studies focus on identifying entities' relations from the semantics of dialogues-they utilize either the attention mechanism or a refined token graph to locate informative words.
Approach: They propose a sequential structure prediction task to incrementally parse SocAoG for dynamic inference upon any incoming utterance.
Outcome: Empirical results show that the proposed model infers social relations more accurately than the state-of-the-art methods.
Gender Biases in Automatic Evaluation Metrics for Image Captioning (2023.emnlp-main)

Copied to clipboard

Challenge: Pretrained evaluation metrics can perpetuate and amplify biases, causing inability to differentiate between biased and unbiased generations.
Approach: They conduct a systematic study of gender biases in image captioning tasks . they show that pretrained models perpetuate and amplify biase .
Outcome: The proposed model-based evaluation metrics have shown good correlations with human judgments in language generation tasks.
Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models have significantly enhanced performance across various NLP tasks . high computational costs and latency associated with deploying such models pose bottlenecks .
Approach: They propose a dynamic hybrid inference framework that efficiently selects between a strong and a weak LLM based on the complexity of the query.
Outcome: The proposed method outperforms existing routing strategies by up to 5.29% in APGR . large models often introduce higher latency, making them less suitable for real-time or resource-constrained applications.
Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration (2025.acl-long)

Copied to clipboard

Challenge: Efficient data selection is crucial to accelerate the pretraining of language models . limited research has addressed the inherent conflicts between data selection methods .
Approach: They propose a multi-actor collaborative data selection mechanism that prioritizes data based on its specific criterion and updates prioritization rules using the current state of the model.
Outcome: The proposed model accelerates convergence in LM pretraining and achieves an average relative performance gain of 10.5% across multiple language model benchmarks.
VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing evaluation methods focus on object hallucinations, focusing on object outputs . current evaluation methods struggle to address subtle semantic distinctions between outputs and reference data .
Approach: They propose a multi-dimensional benchmark covering objects, attributes, and relations . they propose metric that generalizes CHAIR metric and incorporates faithfulness and coverage .
Outcome: The proposed evaluation framework is more comprehensive and better correlated with humans than existing evaluation methods.
Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation (2024.findings-emnlp)

Copied to clipboard

Challenge: Current LLMs are achieving better performance on various benchmarks, but their performance in practical applications does not always match their benchmark results.
Approach: They propose to detect and rewrite leaked benchmarks without altering their difficulties by using Inference-Time Decontamination (ITD) to mitigate performance inflation caused by memorizing leaked samples.
Outcome: The proposed method reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU.
Evaluating Cultural and Social Awareness of LLM Web Agents (2025.findings-naacl)

Copied to clipboard

Challenge: Existing benchmarks often overlook cultural and social awareness . current evaluations focus on task completion, often ignoring the diverse cultural and socio-cultural backgrounds.
Approach: They propose a benchmark to assess LLM agents’ sensitivity to cultural and social norms across two web-based tasks: online shopping and social discussion forums.
Outcome: The proposed framework evaluates LLM agents’ ability to detect and appropriately respond to norm-violating user queries and observations across two web-based tasks.
MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks for multimodal large language models do not capture real-world clinical complexity.
Approach: They evaluate multilingual, multimodal multimodal models of clinical cases with up to 7 distinct visual clinical evidence types per case.
Outcome: The proposed model outperforms human models on differential diagnosis (DDx) generation and final diagnosis (FDx) selection.
GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models (2025.findings-acl)

Copied to clipboard

Challenge: Foundation models for single-cell RNA sequencing ignore biological prior knowledge encoded in gene regulatory relationships and fail to leverage multi-omics signals.
Approach: They propose a framework that integrates multi-scale gene regulatory networks into RNA foundation model training.
Outcome: The proposed framework improves on state-of-the-art models on three downstream tasks . it integrates multi-scale gene regulatory networks (GRNs) from multi-omics data into training .
Revisiting the Knowledge Injection Frameworks (2023.emnlp-main)

Copied to clipboard

Challenge: Injecting unaligned knowledge tuple into large language models achieves comparable (and sometimes better) results than aligned knowledge.
Approach: They propose a technique to inject random knowledge into large language models to improve performance.
Outcome: The proposed technique overcomes the sanity problem and pushes the performance limit.
NumNet: Machine Reading Comprehension with Numerical Reasoning (D19-1)

Copied to clipboard

Challenge: Existing numerical MRC models are weak in numerical reasoning, such as addition, subtraction, sorting and counting.
Approach: They propose a numerical MRC model that integrates numerical reasoning into existing MRC models and achieves an EM-score of 64.56% on the DROP dataset.
Outcome: The proposed model outperforms all existing machine reading comprehension models by considering the numerical relations among numbers on the DROP dataset.
HistLens: Mapping Idea Change across Concepts and Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to diachronic semantics and discourse analysis focus on a single concept or corpus, argues a new paper.
Approach: They propose a framework for multi-concept, multi-corpus conceptual-history analysis that decomposes concept representations into interpretable features and tracks activation dynamics over time and across sources.
Outcome: The proposed framework decomposes concept representations into interpretable features and tracks their activation dynamics over time and across sources.
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations .
Approach: They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models .
Outcome: The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset.
Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: Existing non-autoregressive neural machine translation models suffer from multi-modality problem . despite their autoregressivity, most NMT models suffer with slow decoding speed .
Approach: They propose a semi-autoregressive model which generates a translation as a sequence of segments while each segment is predicted token-by-token.
Outcome: The proposed model can achieve 4 times speedup while maintaining comparable performance.
AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for evaluating factual consistency of abstractive summarization lack coherence or error-type coverage.
Approach: They propose a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) they use a selection module NegFilter to ensure the quality of the generated negative examples .
Outcome: The proposed framework outperforms existing systems on the AggreFact-SOTA benchmark and provides high error-type coverage.
Calibrating the Confidence of Large Language Models by Eliciting Fidelity (2024.emnlp-main)

Copied to clipboard

Challenge: Large language models with RLHF and RLAIF have good alignment but exhibit overconfidence post-alignment.
Approach: They propose a plug-and-play method to estimate the confidence of large language models.
Outcome: The proposed method has shown good calibration performance on 6 RLHF-LMs on four MCQA datasets.
BASES: Large-scale Web Search User Simulation with Large Language Model based Agents (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing research on web search rely on real-user experiments, which can be costly to scale up.
Approach: They propose a user simulation framework with LLM-based agents that can generate unique user profiles at scale.
Outcome: The proposed framework can generate unique user profiles at scale, leading to diverse search behaviors.
Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design (2025.naacl-long)

Copied to clipboard

Challenge: Using Mixture-of-Experts, researchers have found that efficient MoE is difficult to achieve due to two key reasons: imbalanced expert activation and massive communication overhead.
Approach: They propose a collaboration-constrained routing strategy that encourages more specialized expert groups and leverages expert specialization.
Outcome: The proposed approach achieves an average performance improvement of 0.51% and 0.33% on LLaMA-MoE and Qwen-MaE respectively.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Copied to clipboard

Challenge: Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach: They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome: The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors (2023.acl-long)

Copied to clipboard

Challenge: Large language models pre-trained on massive corpora have shown impressive few-shot learning ability on many NLP tasks.
Approach: They propose to recast structured output in the form of code instead of natural language and use generative LLMs of code to perform IE tasks.
Outcome: The proposed method outperforms fine-tuning moderate-size pre-trained models and prompting NL-LLMs under few-shot settings.

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