Image de couverture de livre

Better Explain Transformers by Illuminating Important Information

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Song, Linxin, Cui, Yan, Luo, Ao, Lecue, Freddy, Li, Irene
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

KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking
par: Zhang, Jiawei, et autres
Publié: (2024)

Leveraging Large Language Models for Concept Graph Recovery and Question Answering in NLP Education
par: Yang, Rui, et autres
Publié: (2024)

Graphusion: Leveraging Large Language Models for Scientific Knowledge Graph Fusion and Construction in NLP Education
par: Yang, Rui, et autres
Publié: (2024)

Adaptive In-conversation Team Building for Language Model Agents
par: Song, Linxin, et autres
Publié: (2024)

The Hallucination Tax of Reinforcement Finetuning
par: Song, Linxin, et autres
Publié: (2025)

TacoERE: Cluster-aware Compression for Event Relation Extraction
par: Guan, Yong, et autres
Publié: (2024)

Explaining Length Bias in LLM-Based Preference Evaluations
par: Hu, Zhengyu, et autres
Publié: (2024)

Interpretable LLM-based Table Question Answering
par: Nguyen, Giang, et autres
Publié: (2024)

RSQ: Learning from Important Tokens Leads to Better Quantized LLMs
par: Sung, Yi-Lin, et autres
Publié: (2025)

Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective
par: Yang, Rui, et autres
Publié: (2024)

Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better?
par: Greschner, Lynn, et autres
Publié: (2025)

LeDex: Training LLMs to Better Self-Debug and Explain Code
par: Jiang, Nan, et autres
Publié: (2024)

Explaining Text Similarity in Transformer Models
par: Vasileiou, Alexandros, et autres
Publié: (2024)

Byte Latent Transformer: Patches Scale Better Than Tokens
par: Pagnoni, Artidoro, et autres
Publié: (2024)

Better Synthetic Data by Retrieving and Transforming Existing Datasets
par: Gandhi, Saumya, et autres
Publié: (2024)

Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
par: Shi, Taiwei, et autres
Publié: (2025)

Sentiment analysis with adaptive multi-head attention in Transformer
par: Meng, Fanfei, et autres
Publié: (2023)

How to Discern Important Urgent News?
par: Vasilyev, Oleg, et autres
Publié: (2024)

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
par: Hsu, Aliyah R., et autres
Publié: (2023)

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
par: Yang, Yuqing, et autres
Publié: (2026)

Explaining Relationships Among Research Papers
par: Li, Xiangci, et autres
Publié: (2024)

Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
par: Xu, Haobo, et autres
Publié: (2026)

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
par: Dang, Meihua, et autres
Publié: (2026)

Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
par: Li, Yang, et autres
Publié: (2025)

LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important
par: Liang, Manlai, et autres
Publié: (2025)

How Important is `Perfect' English for Machine Translation Prompts?
par: Schmidtová, Patrícia, et autres
Publié: (2025)

LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models
par: Abdelhalim, Alhassan, et autres
Publié: (2026)

Learning to Explain: Supervised Token Attribution from Transformer Attention Patterns
par: Mihaila, George
Publié: (2026)

ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
par: Tian, Yuanhe, et autres
Publié: (2023)

Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
par: Yu, Qinan, et autres
Publié: (2026)

Long Is More Important Than Difficult for Training Reasoning Models
par: Shen, Si, et autres
Publié: (2025)

Linear Transformers with Learnable Kernel Functions are Better In-Context Models
par: Aksenov, Yaroslav, et autres
Publié: (2024)

Better RAG using Relevant Information Gain
par: Pickett, Marc, et autres
Publié: (2024)

FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning
par: Pan, Haihui, et autres
Publié: (2026)

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners
par: Luo, Yun, et autres
Publié: (2023)

See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
par: Huang, Youcheng, et autres
Publié: (2024)

Offline Training of Language Model Agents with Functions as Learnable Weights
par: Zhang, Shaokun, et autres
Publié: (2024)

Distilling Algorithmic Reasoning from LLMs via Explaining Solution Programs
par: Li, Jierui, et autres
Publié: (2024)

AlpaGasus: Training A Better Alpaca with Fewer Data
par: Chen, Lichang, et autres
Publié: (2023)

Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
par: Song, Linxin, et autres
Publié: (2025)