Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / tma15/paper-reading-list issues and pull requests

#213 - Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Issue - State: open - Opened by tma15 about 1 year ago

#212 - Fine-tuning Language Models for Factuality

Issue - State: open - Opened by tma15 about 1 year ago

#211 - PROMPT ENGINEERING A PROMPT ENGINEER

Issue - State: open - Opened by tma15 about 1 year ago
Labels: prompt-engineering

#210 - Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework

Issue - State: open - Opened by tma15 about 1 year ago
Labels: COLING, XMLC

#209 - Lost in the Middle: How Language Models Use Long Contexts

Issue - State: open - Opened by tma15 about 1 year ago
Labels: prompt-engineering

#208 - Infusing Context and Knowledge Awareness in Multi-turn Dialog Understanding

Issue - State: open - Opened by tma15 about 1 year ago
Labels: dialogue, EACL

#208 - Infusing Context and Knowledge Awareness in Multi-turn Dialog Understanding

Issue - State: open - Opened by tma15 about 1 year ago
Labels: dialogue, EACL

#207 - A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection

Issue - State: open - Opened by tma15 about 1 year ago
Labels: dialogue, interspeech

#207 - A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection

Issue - State: open - Opened by tma15 about 1 year ago
Labels: dialogue, interspeech

#206 - LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Issue - State: open - Opened by tma15 about 1 year ago
Labels: EMNLP, prompt-engineering

#206 - LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Issue - State: open - Opened by tma15 about 1 year ago
Labels: EMNLP, prompt-engineering

#205 - Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

Issue - State: open - Opened by tma15 about 1 year ago
Labels: ACL, prompt-engineering

#205 - Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

Issue - State: open - Opened by tma15 about 1 year ago
Labels: ACL, prompt-engineering

#204 - Prompting with Pseudo-Code Instructions

Issue - State: open - Opened by tma15 about 1 year ago

#204 - Prompting with Pseudo-Code Instructions

Issue - State: open - Opened by tma15 about 1 year ago

#203 - Textbooks Are All You Need II: phi-1.5 technical report

Issue - State: open - Opened by tma15 about 1 year ago

#203 - Textbooks Are All You Need II: phi-1.5 technical report

Issue - State: open - Opened by tma15 about 1 year ago

#202 - EFFICIENT STREAMING LANGUAGE MODELS WITH ATTENTION SINKS

Issue - State: open - Opened by tma15 about 1 year ago

#202 - EFFICIENT STREAMING LANGUAGE MODELS WITH ATTENTION SINKS

Issue - State: open - Opened by tma15 about 1 year ago

#201 - [KDD23] CADENCE: Offline Category Constrained and Diverse Query Generation for E-commerce Autosuggest

Issue - State: open - Opened by tma15 about 1 year ago

#201 - [KDD23] CADENCE: Offline Category Constrained and Diverse Query Generation for E-commerce Autosuggest

Issue - State: open - Opened by tma15 about 1 year ago

#200 - Out-of-Domain Intent Detection Considering Multi-turn Dialogue Contexts

Issue - State: open - Opened by tma15 over 1 year ago

#200 - Out-of-Domain Intent Detection Considering Multi-turn Dialogue Contexts

Issue - State: open - Opened by tma15 over 1 year ago

#199 - Accelerating Large Language Model Decoding with Speculative Sampling

Issue - State: open - Opened by tma15 over 1 year ago

#199 - Accelerating Large Language Model Decoding with Speculative Sampling

Issue - State: open - Opened by tma15 over 1 year ago

#198 - Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning

Issue - State: open - Opened by tma15 over 1 year ago

#197 - Text Embeddings by Weakly-Supervised Contrastive Pre-training

Issue - State: open - Opened by tma15 over 1 year ago

#197 - Text Embeddings by Weakly-Supervised Contrastive Pre-training

Issue - State: open - Opened by tma15 over 1 year ago

#196 - Preference Ranking Optimization for Human Alignment

Issue - State: open - Opened by tma15 over 1 year ago

#196 - Preference Ranking Optimization for Human Alignment

Issue - State: open - Opened by tma15 over 1 year ago

#195 - Retrieval-augmented Multi-label Text Classification

Issue - State: open - Opened by tma15 over 1 year ago

#195 - Retrieval-augmented Multi-label Text Classification

Issue - State: open - Opened by tma15 over 1 year ago

#194 - Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#194 - Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#193 - Long-range Language Modeling with Self-retrieval

Issue - State: open - Opened by tma15 over 1 year ago

#193 - Long-range Language Modeling with Self-retrieval

Issue - State: open - Opened by tma15 over 1 year ago

#192 - Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Issue - State: open - Opened by tma15 over 1 year ago

#192 - Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Issue - State: open - Opened by tma15 over 1 year ago

#191 - Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Issue - State: open - Opened by tma15 over 1 year ago

#191 - Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Issue - State: open - Opened by tma15 over 1 year ago

#190 - Textbooks Are All You Need

Issue - State: open - Opened by tma15 over 1 year ago

#190 - Textbooks Are All You Need

Issue - State: open - Opened by tma15 over 1 year ago

#189 - Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification

Issue - State: open - Opened by tma15 over 1 year ago

#189 - Large Language Models in the Workplace: A Case Study on Prompt Engineering for Job Type Classification

Issue - State: open - Opened by tma15 over 1 year ago

#188 - CHATDB: AUGMENTING LLMS WITH DATABASES AS THEIR SYMBOLIC MEMORY

Issue - State: open - Opened by tma15 over 1 year ago

#187 - SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#187 - SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#186 - Optimal Partial Transport based Sentence Selection for Long-form Document Matching

Issue - State: open - Opened by tma15 over 1 year ago

#185 - The Impact of Positional Encoding on Length Generalization in Transformers

Issue - State: open - Opened by tma15 over 1 year ago

#184 - Dropout Reduces Underfitting

Issue - State: open - Opened by tma15 over 1 year ago

#182 - How Does Generative Retrieval Scale to Millions of Passages?

Issue - State: open - Opened by tma15 over 1 year ago

#181 - ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

Issue - State: open - Opened by tma15 over 1 year ago
Labels: tool-augmented-llm

#180 - Text Classification via Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago
Labels: document-classification

#179 - Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation

Issue - State: open - Opened by tma15 over 1 year ago

#178 - ResiDual: Transformer with Dual Residual Connections

Issue - State: open - Opened by tma15 over 1 year ago

#177 - Search-in-the-Chain: Towards Accurate, Credible and Traceable Large Language Models for Knowledge-intensive Tasks

Issue - State: open - Opened by tma15 over 1 year ago

#177 - Search-in-the-Chain: Towards Accurate, Credible and Traceable Large Language Models for Knowledge-intensive Tasks

Issue - State: open - Opened by tma15 over 1 year ago

#176 - Unlimiformer: Long-Range Transformers with Unlimited Length Input

Issue - State: open - Opened by tma15 over 1 year ago

#176 - Unlimiformer: Long-Range Transformers with Unlimited Length Input

Issue - State: open - Opened by tma15 over 1 year ago

#175 - SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation

Issue - State: open - Opened by tma15 over 1 year ago

#175 - SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation

Issue - State: open - Opened by tma15 over 1 year ago

#174 - ART: Automatic multi-step reasoning and tool-use for large language models

Issue - State: open - Opened by tma15 over 1 year ago

#174 - ART: Automatic multi-step reasoning and tool-use for large language models

Issue - State: open - Opened by tma15 over 1 year ago

#173 - Text and Code Embeddings by Contrastive Pre-Training

Issue - State: open - Opened by tma15 over 1 year ago

#173 - Text and Code Embeddings by Contrastive Pre-Training

Issue - State: open - Opened by tma15 over 1 year ago

#172 - GPT4Tools: Teaching LLM to Use Tools via Self-instruction

Issue - State: open - Opened by tma15 over 1 year ago

#172 - GPT4Tools: Teaching LLM to Use Tools via Self-instruction

Issue - State: open - Opened by tma15 over 1 year ago

#171 - Augmented Language Models: a Survey

Issue - State: open - Opened by tma15 over 1 year ago - 1 comment

#171 - Augmented Language Models: a Survey

Issue - State: open - Opened by tma15 over 1 year ago - 1 comment

#170 - Scaling Transformer to 1M tokens and beyond with RMT

Issue - State: open - Opened by tma15 over 1 year ago

#170 - Scaling Transformer to 1M tokens and beyond with RMT

Issue - State: open - Opened by tma15 over 1 year ago

#169 - Why Do Better Loss Functions Lead to Less Transferable Features?

Issue - State: open - Opened by tma15 over 1 year ago
Labels: NeurIPS

#169 - Why Do Better Loss Functions Lead to Less Transferable Features?

Issue - State: open - Opened by tma15 over 1 year ago
Labels: NeurIPS

#168 - Sabiá: Portuguese Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#168 - Sabiá: Portuguese Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#167 - How to train your own Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#167 - How to train your own Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#166 - Mitigating Neural Network Overconfidence with Logit Normalization

Issue - State: open - Opened by tma15 over 1 year ago
Labels: ICML

#166 - Mitigating Neural Network Overconfidence with Logit Normalization

Issue - State: open - Opened by tma15 over 1 year ago
Labels: ICML

#165 - NormSoftmax: Normalize the Input of Softmax to Accelerate and Stabilize Training

Issue - State: open - Opened by tma15 over 1 year ago

#165 - NormSoftmax: Normalize the Input of Softmax to Accelerate and Stabilize Training

Issue - State: open - Opened by tma15 over 1 year ago

#164 - What’s in the RedPajama-Data-1T LLM training set

Issue - State: open - Opened by tma15 over 1 year ago

#164 - What’s in the RedPajama-Data-1T LLM training set

Issue - State: open - Opened by tma15 over 1 year ago

#163 - LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Issue - State: open - Opened by tma15 over 1 year ago

#163 - LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention

Issue - State: open - Opened by tma15 over 1 year ago

#162 - Go smol or go home Why we should train smaller LLMs on more tokens

Issue - State: open - Opened by tma15 over 1 year ago

#162 - Go smol or go home Why we should train smaller LLMs on more tokens

Issue - State: open - Opened by tma15 over 1 year ago

#161 - GLM-130B: AN OPEN BILINGUAL PRE-TRAINED MODEL

Issue - State: open - Opened by tma15 over 1 year ago

#161 - GLM-130B: AN OPEN BILINGUAL PRE-TRAINED MODEL

Issue - State: open - Opened by tma15 over 1 year ago

#160 - Self-Refine: Iterative Refinement with Self-Feedback

Issue - State: open - Opened by tma15 over 1 year ago

#160 - Self-Refine: Iterative Refinement with Self-Feedback

Issue - State: open - Opened by tma15 over 1 year ago

#159 - LLaMA: Open and Efficient Foundation Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#159 - LLaMA: Open and Efficient Foundation Language Models

Issue - State: open - Opened by tma15 over 1 year ago

#158 - Instruction Tuning with GPT-4

Issue - State: open - Opened by tma15 over 1 year ago

#158 - Instruction Tuning with GPT-4

Issue - State: open - Opened by tma15 over 1 year ago

#157 - AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators

Issue - State: open - Opened by tma15 over 1 year ago

#157 - AnnoLLM: Making Large Language Models to Be Better Crowdsourced Annotators

Issue - State: open - Opened by tma15 over 1 year ago

#156 - Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster

Issue - State: open - Opened by tma15 over 1 year ago

#156 - Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster

Issue - State: open - Opened by tma15 over 1 year ago

#155 - More than you’ve asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models

Issue - State: open - Opened by tma15 over 1 year ago