SOTAVerified

Long Form Question Answering

Long-form question answering is a task requiring elaborate and in-depth answers to open-ended questions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 61 papers

TitleStatusHype
Learning to Plan and Generate Text with Citations—0
CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systemsCode1
Attribute First, then Generate: Locally-attributable Grounded Text GenerationCode1
Multi-Review Fusion-in-Context—0
ALaRM: Align Language Models via Hierarchical Rewards ModelingCode1
KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking TechniquesCode2
Genie: Achieving Human Parity in Content-Grounded Datasets Generation—0
Reinforcement Replaces Supervision: Query focused Summarization using Deep Reinforcement LearningCode0
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback—0
Long-form Question Answering: An Iterative Planning-Retrieval-Generation Approach—0
SEMQA: Semi-Extractive Multi-Source Question AnsweringCode1
Adapting Pre-trained Generative Models for Extractive Question Answering—0
PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering—0
Understanding Retrieval Augmentation for Long-Form Question Answering—0
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference OptimizationCode1
A Novel Computational and Modeling Foundation for Automatic Coherence Assessment—0
Investigating Answerability of LLMs for Long-Form Question Answering—0
Fine-Grained Human Feedback Gives Better Rewards for Language Model TrainingCode2
Concise Answers to Complex Questions: Summarization of Long-form AnswersCode0
A Critical Evaluation of Evaluations for Long-form Question AnsweringCode1
Revisiting Sentence Union Generation as a Testbed for Text ConsolidationCode0
WebCPM: Interactive Web Search for Chinese Long-form Question AnsweringCode2
Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive TasksCode1
LongForm: Effective Instruction Tuning with Reverse InstructionsCode2
Generative Long-form Question Answering: Relevance, Faithfulness and Succinctness—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.