Learning to Maximize Mutual Information for Chain-of-Thought Distillation
Comments Accepted to ACL 2024 Findings
期刊&会议
ACL
Annual Meeting of the Association for Computational Linguistics · 会议 · Natural Language Processing
Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics
Comments Accepted to Findings of ACL 2024
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
Comments Accepted to ACL2024 (Main Proceedings)
VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models
Comments Accepted to ACL 2024
Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data
Comments Findings of ACL 2024. Project website: https://xxxiaol.github.io/QRData/
Set the Clock: Temporal Alignment of Pretrained Language Models
Comments Accepted as Findings of ACL 2024. Our code and data is available at https://github.com/yizhongw/llm-temporal-alignment
The Hidden Space of Transformer Language Adapters
Comments Accepted to ACL 2024 (main conference)
Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?
Comments ACL 2024
Emergent Word Order Universals from Cognitively-Motivated Language Models
Comments Accepted by ACL 2024 main conference, 22 pages
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
Comments Accepted to ACL 24 Findings
Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
Comments ACL2024 findings, Camera-ready
Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
Comments ACL2024 (findings), Camera-ready
Benchmarking Large Language Models on Communicative Medical Coaching: a Novel System and Dataset
Comments Accepted to Findings of the Association for Computational Linguistics: ACL 2024
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models
Comments 14 pages, 8 figures, 7 tables - to be published at ACL 2024
Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning
Comments ACL2024 main, Camera-ready
CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities
Comments ACL 2024 (Findings). Project website at https://yujunmao1.github.io/CHAMP/
Do Androids Know They're Only Dreaming of Electric Sheep?
Comments ACL 2024 (Findings) Camera-Ready
It's Not Easy Being Wrong: Large Language Models Struggle with Process of Elimination Reasoning
Comments ACL 2024 (Findings)
Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor
Comments To appear in ACL 2024 Main
Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering
Comments Accepted by ACL 2024 (Findings). Code is available at https://github.com/zjukg/KnowPAT
Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning
Comments Accepted in Association for Computational Linguistics (ACL) 2024 Findings
Fooling the Textual Fooler via Randomizing Latent Representations
Comments Accepted to Findings of ACL 2024
DAPR: A Benchmark on Document-Aware Passage Retrieval
Comments Accepted at ACL 2024 Main Conference
Compositional Generalization with Grounded Language Models
Comments ACL 2024, Findings
MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter
Comments ACL 24
A Deep Dive into the Trade-Offs of Parameter-Efficient Preference Alignment Techniques
Comments Accepted to ACL (Main) 2024
Uncertainty Aware Learning for Language Model Alignment
Comments ACL 2024
On The Persona-based Summarization of Domain-Specific Documents
Journal ref ACL 2024 Findings (Association for Computational Linguistics)
DORY: Deliberative Prompt Recovery for LLM
Comments Findings of ACL 2024
The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models
Comments To be published in ACL 2024. 19 pages, 2 figures
