Picture for Neel Jain

Neel Jain

Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models

Add code
Dec 09, 2024
Viaarxiv icon

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Add code
Jun 27, 2024
Viaarxiv icon

GenQA: Generating Millions of Instructions from a Handful of Prompts

Add code
Jun 14, 2024
Figure 1 for GenQA: Generating Millions of Instructions from a Handful of Prompts
Figure 2 for GenQA: Generating Millions of Instructions from a Handful of Prompts
Figure 3 for GenQA: Generating Millions of Instructions from a Handful of Prompts
Figure 4 for GenQA: Generating Millions of Instructions from a Handful of Prompts
Viaarxiv icon

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

Add code
Jun 14, 2024
Viaarxiv icon

Transformers Can Do Arithmetic with the Right Embeddings

Add code
May 27, 2024
Figure 1 for Transformers Can Do Arithmetic with the Right Embeddings
Figure 2 for Transformers Can Do Arithmetic with the Right Embeddings
Figure 3 for Transformers Can Do Arithmetic with the Right Embeddings
Figure 4 for Transformers Can Do Arithmetic with the Right Embeddings
Viaarxiv icon

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Add code
Oct 10, 2023
Viaarxiv icon

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Add code
Sep 04, 2023
Figure 1 for Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Figure 2 for Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Figure 3 for Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Figure 4 for Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Viaarxiv icon

Bring Your Own Data! Self-Supervised Evaluation for Large Language Models

Add code
Jun 29, 2023
Viaarxiv icon

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Add code
Feb 07, 2023
Figure 1 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
Figure 2 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
Figure 3 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
Figure 4 for Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
Viaarxiv icon