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 17, 2024

SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation
Junyu Luo, Xiao Luo, Xiusi Chen, Zhiping Xiao, Wei Ju, Ming Zhang
Large Language Model Fine Tuning Domain Specific Supervised Fine Tuning LLM Fine Tuning LLM Adaptation
Persistent Pre-Training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov, Jianfeng Chi, Eric Michael Smith, Nicholas Carlini, Florian Tramèr, Daphne Ippolito
Large Language Model Language Model Medical LLM Poisoning Attack
On the Role of Attention Heads in Large Language Model Safety
Zhenhong Zhou, Haiyang Yu, Xinghua Zhang, Rongwu Xu, Fei Huang, Kun Wang, Yang Liu, Junfeng Fang, Yongbin Li
Large Language Model Integral Role Multi Head Attention Attention Head Model Safety Safety Critical
Unconstrained Model Merging for Enhanced LLM Reasoning
Yiming Zhang, Baoyi He, Shengyu Zhang, Yuhao Fu, Qi Zhou, Zhijie Sang, Zijin Hong, Kejing Yang, Wenjun Wang, Jianbo Yuan, Guangning Han, Linyi Li, Chunlin Ji, Fei Wu, Hongxia Yang
Large Language Model LLM Reasoning Model Merging
HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings
Varun Gumma, Anandhita Raghunath, Mohit Jain, Sunayana Sitaram
Large Language Model Retrieval Augmented Generation Real World Indian Language Multilingual Scenario Multilingual Evaluation RAG Based
SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs
Yuling Gu, Oyvind Tafjord, Hyunwoo Kim, Jared Moore, Ronan Le Bras, Peter Clark, Yejin Choi
Large Language Model Human Mind Implicit Language Mental State
Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors
Anthony Sicilia, Malihe Alikhani
Large Language Model Chain of Thought Mitigating Bias Open Source Language Model Eliciting Knowledge Online Content Moderation
Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?
Virgile Rennard, Christos Xypolopoulos, Michalis Vazirgiannis
Large Language Model Absolute Stance Bias New Attack Etruscan Mirror Harmful Content Self Rationalization
MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs
Andreas Opedal, Haruki Shirakami, Bernhard Schölkopf, Abulhair Saparov, Mrinmaya Sachan
Large Language Model Strong Generalization Related Problem Proof System Distribution Input Mathematical Proof Arithmetic Circuit Algorithmic Arbitrariness
IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection
Jielin Song, Siyu Liu, Bin Zhu, Yanghui Rao
Large Language Model High Efficiency Instruction Tuning Iterative Training Instruction Data Instruction Quality
Progressive Mixed-Precision Decoding for Efficient LLM Inference
Hao Mark Chen, Fuwen Tan, Alexandros Kouris, Royson Lee, Hongxiang Fan, Stylianos I. Venieris
Large Language Model LLM Inference Language Task Uniform Quantization
MedINST: Meta Dataset of Biomedical Instructions
Wenhan Han, Meng Fang, Zihan Zhang, Yu Yin, Zirui Song, Ling Chen, Mykola Pechenizkiy, Qingyu Chen
Large Language Model Human Instruction Instructional Video Meta Dataset Biomedical NLP Task
Augmentation Policy Generation for Image Classification Using Large Language Models
Ant Duru, Alptekin Temizel
Large Language Model Language Model Deep Learning Model Image Classification Data Augmentation Method Augmentation Pipeline Augmentation Policy
Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models
Chengyu Du, Jinyi Han, Yizhou Ying, Aili Chen, Qianyu He, Haokun Zhao, Sirui Xia, Haoran Guo, Jiaqing Liang, Zulong Chen, Liangyue Li, Yanghua Xiao
Large Language Model Language Model Iterative Refinement Face Act
LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights
Odysseas S. Chlapanis, Dimitrios Galanis, Ion Androutsopoulos
Large Language Model Case Relevance Reasoning Benchmark Legal Document Legal Reasoning Human Right Legal Argument
Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement
Yuxuan Liu, Wenyuan Li, Laizhong Cui, Hailiang Yang
Large Language Model Efficient Inference Inference Efficiency Inference Speed Parallel Decoding Auto Regressive Decoding
Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
Ingeol Baek, Hwan Chang, Byeongjeong Kim, Jimin Lee, Hwanhee Lee
Large Language Model Language Model Retrieval Augmented Generation App to App Retrieval Selective Engagement Iterative Retrieval
Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems
Isack Lee, Haebin Seong
Large Language Model AI System Jailbreak Attack Social Bias Safety Alignment Malicious Traffic Common Bias Moral Bias
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models
David Hoffmann, Kailash Budhathoki, Matthaeus Kleindessner
Large Language Model Medical LLM Edge Pruning Pruning Method Centrality Measure Node Importance Graph Theoretic
Advancing Large Language Model Attribution through Self-Improving
Lei Huang, Xiaocheng Feng, Weitao Ma, Liang Zhao, Yuchun Fan, Weihong Zhong, Dongliang Xu, Qing Yang, Hongtao Liu, Bing Qin
Large Language Model Attribution Score Self Improvement Language Model Attribution

Large Language Model

Papers

SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation

Persistent Pre-Training Poisoning of LLMs

On the Role of Attention Heads in Large Language Model Safety

Unconstrained Model Merging for Enhanced LLM Reasoning

HEALTH-PARIKSHA: Assessing RAG Models for Health Chatbots in Real-World Multilingual Settings

SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs

Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors

Bias in the Mirror: Are LLMs opinions robust to their own adversarial attacks ?

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

IterSelectTune: An Iterative Training Framework for Efficient Instruction-Tuning Data Selection

Progressive Mixed-Precision Decoding for Efficient LLM Inference

MedINST: Meta Dataset of Biomedical Instructions

Augmentation Policy Generation for Image Classification Using Large Language Models

Think Thrice Before You Act: Progressive Thought Refinement in Large Language Models

LAR-ECHR: A New Legal Argument Reasoning Task and Dataset for Cases of the European Court of Human Rights

Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement

Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval

Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems

LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models

Advancing Large Language Model Attribution through Self-Improving