Large Language Model

Large language models (LLMs) are sophisticated AI systems designed to process and generate human-like text, aiming to improve various natural language processing tasks. Current research focuses on enhancing LLM safety, efficiency (through techniques like quantization and optimized decoding), and fairness, as well as improving their ability to perform complex reasoning and handle diverse instructions. These advancements are significant because they address critical limitations in current LLMs and pave the way for broader applications across diverse fields, including healthcare, legal tech, and autonomous systems.

Papers

October 16, 2024

BenchmarkCards: Large Language Model and Risk Reporting
Anna Sokol, Nuno Moniz, Elizabeth Daly, Michael Hind, Nitesh Chawla
Large Language Model New Benchmark LLM Benchmark
Self-Pluralising Culture Alignment for Large Language Models
Shaoyang Xu, Yongqi Leng, Linhao Yu, Deyi Xiong
Large Language Model Cultural Background Pluralistic Alignment Cultural Alignment
Large Language Models as a Tool for Mining Object Knowledge
Hannah YoungEun An, Lenhart K. Schubert
Large Language Model Knowledge Graph Commonsense Knowledge BRIO Tool Knowledge Base Construction
Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
Mingyang Chen, Haoze Sun, Tianpeng Li, Fan Yang, Hao Liang, Keer Lu, Bin Cui, Wentao Zhang, Zenan Zhou, Weipeng Chen
Large Language Model Instruction Tuning Compositional Ability Instruction Generation Compositional Task
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite
Large Language Model Inherent Interpretability Machine Unlearning Human Editing Knowledge Editing Robust Unlearning Language Model Performance
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, Zhaoxuan Tan, Chao Shen, Meng Jiang
Large Language Model Mathematical Reasoning Answer Correctness Best of N
Interpreting token compositionality in LLMs: A robustness analysis
Nura Aljaafari, Danilo S. Carvalho, André Freitas
Large Language Model Robustness Analysis Compound Token Compositional Nature
Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception
Jihao Zhao, Zhiyuan Ji, Pengnian Qi, Simin Niu, Bo Tang, Feiyu Xiong, Zhiyu Li
Large Language Model Retrieval Augmented Generation Perception Aware Chunk Wise Text Segmentation Perplexity Analysis
In-Context Learning Enables Robot Action Prediction in LLMs
Yida Yin, Zekai Wang, Yuvan Sharma, Dantong Niu, Trevor Darrell, Roei Herzig
Large Language Model Reinforcement Learning Context Learning Robot Action Textual Description
Evaluating Morphological Compositional Generalization in Large Language Models
Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Lonneke van der Plas, Duygu Ataman
Large Language Model Full Model Large Language Linguistic Generalization
Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning
Ruimeng Ye, Yang Xiao, Bo Hui
Large Language Model Legal Reasoning Non Toxic Pilot Study Weak to Strong Task Alignment Fast Generation Alignment Task
Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning
Vernon Y.H. Toh, Deepanway Ghosal, Soujanya Poria
Large Language Model Language Model Mathematical Reasoning Reasoning Path Self Consistency Reasoning Problem Past Present Temporal Program Mathematical Reasoning Task State of the Art Verifier Software Verification
CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
Yixi Ding, Jiaying Wu, Tongyao Zhu, Yanxia Qin, Qian Liu, Min-Yen Kan
Large Language Model Medical LLM Fine Grained Control Scientific Summarization Controllable Summarization Compositional Capability
On the Utility of Domain Modeling Assistance with Large Language Models
Meriem Ben Chaaben, Lola Burgueño, Istvan David, Houari Sahraoui
Large Language Model Task Utility Model Driven Domain Model Completion Method Modeling Language
FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion
Jiacheng Ruan, Yebin Yang, Zehao Lin, Feiyu Xiong, Zeyun Tang, Zhiyu Li
Large Language Model Large Vision Language Model Image Understanding Input Image
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL
Jared Joselowitz, Arjun Jagota, Satyapriya Krishna, Sonali Parbhoo
Large Language Model DCU Insight AQ Inverse Reinforcement Learning Reward Model Toxicity Detection LLM Training Inverse Task Implicit Reward
Mastering the Craft of Data Synthesis for CodeLLMs
Meng Chen, Philip Arthur, Qianyu Feng, Cong Duy Vu Hoang, Yu-Heng Hong, Mahdi Kazemi Moghaddam, Omid Nezami, Thien Nguyen, Gioacchino Tangari, Duy Vu, Thanh Vu, Mark Johnson, Krishnaram Kenthapadi, Don Dharmasiri, Long Duong, Yuan-Fang Li
Large Language Model Data Synthesis Code LLM Traditional CrAFT Filter Design
KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs
Yongqin Xu, Huan Li, Ke Chen, Lidan Shou
Large Language Model Fine Tuned Large Language Model Entity Matching Natural Language Task Description Unstructured Knowledge Schema Information
The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph
Minghao Wu, Thuy-Trang Vu, Lizhen Qu, Gholamreza Haffari
Large Language Model Natural Language Raw Data NLP Field Diversity Awareness Quality Issue View Selection N Gram Graph Filter Bipartite Graph
Conformity in Large Language Models
Xiaochen Zhu, Caiqi Zhang, Tom Stafford, Nigel Collier, Andreas Vlachos
Large Language Model Conformity Bias

Large Language Model

Papers

BenchmarkCards: Large Language Model and Risk Reporting

Self-Pluralising Culture Alignment for Large Language Models

Large Language Models as a Tool for Mining Object Knowledge

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction

Interpreting token compositionality in LLMs: A robustness analysis

Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception

In-Context Learning Enables Robot Action Prediction in LLMs

Evaluating Morphological Compositional Generalization in Large Language Models

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning

Not All Votes Count! Programs as Verifiers Improve Self-Consistency of Language Models for Math Reasoning

CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization

On the Utility of Domain Modeling Assistance with Large Language Models

FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion

Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL

Mastering the Craft of Data Synthesis for CodeLLMs

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph

Conformity in Large Language Models