Image de couverture de livre

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Saeidi, Amir, Verma, Shivanshu, Uddin, Md Nayem, Baral, Chitta
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization
par: Saeidi, Amir, et autres
Publié: (2024)

When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers
par: Handa, Divij, et autres
Publié: (2024)

Chaos with Keywords: Exposing Large Language Models Sycophantic Hallucination to Misleading Keywords and Evaluating Defense Strategies
par: RRV, Aswin, et autres
Publié: (2024)

From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
par: Uddin, Md Nayem, et autres
Publié: (2026)

UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' Memorization
par: Uddin, Md Nayem, et autres
Publié: (2024)

Investigating and Addressing Hallucinations of LLMs in Tasks Involving Negation
par: Varshney, Neeraj, et autres
Publié: (2024)

ThinkTuning: Instilling Cognitive Reflections without Distillation
par: RRV, Aswin, et autres
Publié: (2025)

FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
par: Saeidi, Amir, et autres
Publié: (2026)

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench
par: Mishra, Venkatesh, et autres
Publié: (2025)

The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness
par: Varshney, Neeraj, et autres
Publié: (2023)

Asking and Answering Questions to Extract Event-Argument Structures
par: Uddin, Md Nayem, et autres
Publié: (2024)

Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction
par: Uddin, Md Nayem, et autres
Publié: (2024)

Cutting Through the Noise: Boosting LLM Performance on Math Word Problems
par: Anantheswaran, Ujjwala, et autres
Publié: (2024)

ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
par: Patel, Maitreya, et autres
Publié: (2023)

Map&Make: Schema Guided Text to Table Generation
par: Ahuja, Naman, et autres
Publié: (2025)

ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution
par: Alqurnawi, Yahia, et autres
Publié: (2026)

Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective
par: Rajput, Krishna Singh, et autres
Publié: (2025)

$λ$-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space
par: Patel, Maitreya, et autres
Publié: (2024)

GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent Reasoning
par: Siingh, Shikhhar, et autres
Publié: (2025)

SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection
par: Riad, Md. Shihab Uddin
Publié: (2026)

Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
par: Gupta, Himanshu, et autres
Publié: (2024)

VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks
par: Sampat, Shailaja Keyur, et autres
Publié: (2024)

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time
par: Handa, Divij, et autres
Publié: (2025)

Cat-DPO: Category-Adaptive Safety Alignment
par: Yang, Tiankai, et autres
Publié: (2026)

TarGEN: Targeted Data Generation with Large Language Models
par: Gupta, Himanshu, et autres
Publié: (2023)

Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study
par: Xu, Shusheng, et autres
Publié: (2024)

Mask-DPO: Generalizable Fine-grained Factuality Alignment of LLMs
par: Gu, Yuzhe, et autres
Publié: (2025)

Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions
par: Parmar, Mihir, et autres
Publié: (2022)

Robust Multi-Objective Preference Alignment with Online DPO
par: Gupta, Raghav, et autres
Publié: (2025)

Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models
par: Patel, Nisarg, et autres
Publié: (2024)

Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents
par: Kumbhar, Shrinidhi, et autres
Publié: (2025)

PHANTOM RECALL: When Familiar Puzzles Fool Smart Models
par: Mukhopadhyay, Souradeep, et autres
Publié: (2025)

ShishuLM : Achieving Optimal and Efficient Parameterization with Low Attention Transformer Models
par: Kumar, Shivanshu, et autres
Publié: (2025)

VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning
par: Yilmaz, Nilay, et autres
Publié: (2025)

Dual Caption Preference Optimization for Diffusion Models
par: Saeidi, Amir, et autres
Publié: (2025)

MixDPO: Modeling Preference Strength for Pluralistic Alignment
par: Imai, Saki, et autres
Publié: (2026)

LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
par: Parmar, Mihir, et autres
Publié: (2024)

Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
par: Samuel, Vinay, et autres
Publié: (2026)

Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
par: Xiao, Teng, et autres
Publié: (2024)

Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs
par: Mohammadi, Hadi, et autres
Publié: (2025)