Papers by Chenyang Lyu

17 papers
ReFreeKV: Towards Threshold-Free KV Cache Compression (2026.findings-acl)

Copied to clipboard

Challenge: Towards the KV cache efficiency, we propose a new objective that lifts the threshold constraints for robust KV compression.
Approach: They propose a method that adjusts KV cache budgets while preserving full-cache performance.
Outcome: The proposed method can reduce memory consumption while preserving full-cache performance.
Improving Document-Level Sentiment Analysis with User and Product Context (2020.coling-main)

Copied to clipboard

Challenge: Existing work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review.
Approach: They propose to incorporate all available historical review text belonging to the author of the review in question and investigate the inclusion of his- torical reviews associated with the current product.
Outcome: The proposed model improves on IMDB, Yelp 2013 and Yelpan 2014 datasets by more than 2 percentage points in the best case.
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on functional relevance while neglecting code quality.
Approach: They propose a multilingual benchmark to evaluate quality-aware code retrieval . they include fine-grained quality annotations over 42,725 queries and 134,907 code snippets .
Outcome: The proposed benchmarks show that state-of-the-art models fail to separate buggy or insecure code from robust counterparts.
Out-of-Distribution Generalization in Natural Language Processing: Past, Present, and Future (2023.emnlp-main)

Copied to clipboard

Challenge: Existing literature on the generalization of machine learning models to out-of-distribution data is lacking.
Approach: They propose to present the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
Outcome: The proposed survey provides the first comprehensive review of recent progress, methods, and evaluations on the generalization challenge from an OOD perspective in natural language understanding.
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach: They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome: The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.
Semantic-Aware Dynamic Retrospective-Prospective Reasoning for Event-Level Video Question Answering (2023.acl-srw)

Copied to clipboard

Challenge: Event-Level Video Question Answering (EVQA) requires complex reasoning across video events to obtain the visual information needed to provide optimal answers.
Approach: They propose a semantic-aware dynamic retrospective-prospective reasoning approach for video-based question answering that explicitly uses the Semantic Role Labeling (SRL) structure of the question in the dynamic reasoning process.
Outcome: The proposed model outperforms existing models on a trafficQA benchmark dataset.
Exploiting Rich Textual User-Product Context for Improving Personalized Sentiment Analysis (2023.findings-acl)

Copied to clipboard

Challenge: Typical approaches do not exploit the potential of historical reviews or do not make full use of user/product associations.
Approach: They propose to use historical reviews to initialize user and product representations and incorporate textual associations via a user-product cross-context module.
Outcome: The proposed method outperforms existing state-of-the-art models on IMDb, Yelp and Longformer benchmarks.
Benchmarking and Improving Long-Text Translation with Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Recent studies have illuminated the promising capabilities of large language models (LLMs) in handling long texts.
Approach: They construct a benchmark dataset specifically designed for the finetuning and evaluation of large language models (LLMs) they compare LLMs with MT models and find they exhibit shortcomings in long-text domains .
Outcome: The proposed model performs better in long-text translation, and its performance diminishes as document size increases.
Document-Level Machine Translation with Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing tasks.
Approach: They examine the impact of different prompts on document-level translation quality and discourse phenomena using figures and lines, which are invisible to GPT-4.
Outcome: The proposed models outperform commercial MT systems and advanced document-level MT methods on a number of benchmarks and show potential to become a new paradigm for document- level translation.
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration (2025.findings-acl)

Copied to clipboard

Challenge: Existing safety calibration methods focus on model undersafety, where the model responds to hazardous queries, while neglecting oversafetiness, where models refuse to answer safe queries.
Approach: They propose safety calibration which addresses both undersafety and oversafetiness by comparing model responses to a novel dataset of 3,600 image-text pairs.
Outcome: The proposed methods have been used to evaluate safety calibration across image-centric and text-centric scenarios.
HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Hallucination is a significant challenge for large language models, but current methods struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability.
Approach: They propose a method that captures the full dynamics of large language models by using neural differential equations to assess the truthfulness of statements.
Outcome: The proposed method achieves 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art methods.
From Multiple-Choice to Extractive QA: A Case Study for English and Arabic (2025.coling-main)

Copied to clipboard

Challenge: Recent years have brought about very fast developments in Natural Language Processing (NLP), but many other languages are overlooked due to limited resources.
Approach: They propose to repurpose a multilingual BELEBELE dataset for a task of extractive QA in the style of machine reading comprehension.
Outcome: The proposed approach could be used to extract QA in the style of machine reading comprehension.
Improving Unsupervised Question Answering via Summarization-Informed Question Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Question Generation (QG) is the production of meaningful questions given a set of input passages and corresponding answers.
Approach: They propose a method which uses questions generated heuristically from news summaries as a source of training data for a QG system.
Outcome: The proposed method outperforms previous unsupervised models on three in-domain datasets and three out-of-domain ones.
Reference-free Hallucination Detection for Large Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large vision-language models exhibit excellent ability in language understanding, question answering, and conversations of visual inputs, but they are prone to producing hallucinations.
Approach: They propose to use supervised uncertainty quantification methods to detect hallucinations in large vision-language models.
Outcome: The proposed methods outperform the others in detecting hallucinations on four representative LVLMs across two different tasks.
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025.acl-long)

Copied to clipboard

Challenge: Recent efforts to distill large reasoning models into smaller lightweight models have shown competitive performances.
Approach: They propose to distill long Chain-of-Thought data to improve SFT and RL methods by constructing data from scratch using Monte Carlo Tree Search.
Outcome: The proposed method significantly improves reasoning performance on various benchmarks such as math (GSM8K, MATH, AIME).
A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are introducing a new phase in machine translation . despite advances in MT, there are still many challenges to overcome .
Approach: They propose to highlight several new directions for MT that are influenced by Large Language Models like GPT-4 and ChatGPT.
Outcome: The proposed models offer vast linguistic understandings and bring innovative methodologies, such as prompt-based techniques, that have the potential to further elevate MT.
Achieving Reliable Human Assessment of Open-Domain Dialogue Systems (2022.acl-long)

Copied to clipboard

Challenge: Evaluation of open-domain dialogue systems is challenging and unreliable . human evaluation of live conversations is highly reliable, but reliability cannot be assumed .
Approach: They propose a method of open-domain dialogue evaluation that is highly reliable . they compare live conversations with models that avoid pre-created reference dialogues .
Outcome: The proposed method is highly reliable while remaining feasible and low cost.

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