Picture for Chen-Yu Lee

Chen-Yu Lee

Reverse Thinking Makes LLMs Stronger Reasoners

Add code
Nov 29, 2024
Viaarxiv icon

Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling

Add code
Oct 15, 2024
Figure 1 for Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Figure 2 for Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Figure 3 for Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Figure 4 for Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Viaarxiv icon

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Add code
Oct 15, 2024
Figure 1 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Figure 2 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Figure 3 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Figure 4 for Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
Viaarxiv icon

TableRAG: Million-Token Table Understanding with Language Models

Add code
Oct 07, 2024
Figure 1 for TableRAG: Million-Token Table Understanding with Language Models
Figure 2 for TableRAG: Million-Token Table Understanding with Language Models
Figure 3 for TableRAG: Million-Token Table Understanding with Language Models
Figure 4 for TableRAG: Million-Token Table Understanding with Language Models
Viaarxiv icon

Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrieval

Add code
Aug 03, 2024
Viaarxiv icon

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Add code
Jul 11, 2024
Figure 1 for Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Figure 2 for Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Figure 3 for Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Figure 4 for Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
Viaarxiv icon

Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization

Add code
Jun 23, 2024
Figure 1 for Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Figure 2 for Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Figure 3 for Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Figure 4 for Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization
Viaarxiv icon

CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation

Add code
Jun 08, 2024
Viaarxiv icon

CodecLM: Aligning Language Models with Tailored Synthetic Data

Add code
Apr 08, 2024
Viaarxiv icon

Unsupervised LLM Adaptation for Question Answering

Add code
Feb 16, 2024
Viaarxiv icon