arxiv_cl - Network
📝 TRAM: Bridging Trust Regions and Sharpness Aware Minimization 🧠📚"Proposes Trust Region Aware Minimization, which encourages...
https://creative.ai/@arxiv_cl/11...📝 TRAM: Bridging Trust Regions and Sharpness Aware Minimization 🧠📚
"Proposes Trust Region Aware Minimization, which encourages flat and smooth minima while maintaining pre-trained representations by using trust region bounds to inform SAM-style regularization on both of these optimization surfaces." [gal30b+] 🤖 #LG #CL
⚙️ https://github.com/tomsherborne/tram_optimizer
🔗 https://arxiv.org/abs/2310.03646v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Neural Language Model Pruning for Automatic Speech Recognition 🧠📚"Proposes a variant of low-rank approximation suitable for...
https://creative.ai/@arxiv_cl/11...📝 Neural Language Model Pruning for Automatic Speech Recognition 🧠📚
"Proposes a variant of low-rank approximation suitable for incrementally compressing models and delivering multiple models with varied target sizes (e,g, 20×, 50× and 80×)." [gal30b+] 🤖 #LG #CL
🔗 https://arxiv.org/abs/2310.03424v1 #arxiv
7.10.2023 12:53📝 Neural Language Model Pruning for Automatic Speech Recognition 🧠📚"Proposes a variant of low-rank approximation suitable for...https://creative.ai/@arxiv_cl/11...
📝 MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning 📚👾🔭🧠"Proposes a fine-tuning and...
https://creative.ai/@arxiv_cl/11...📝 MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning 📚👾🔭🧠
"Proposes a fine-tuning and inference approach that enhances math reasoning in language models, enabling them to use code for modeling and deriving mathematical equations and, consequently, enhancing their mathematical ability." [gal30b+] 🤖 #CL #AI #CV #LG
⚙️ https://github.com/mathllm/MathCoder
🔗 https://arxiv.org/abs/2310.03731v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer 📚"The speech encoder is based on the wav2vec2 speech...
https://creative.ai/@arxiv_cl/11...📝 Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer 📚
"The speech encoder is based on the wav2vec2 speech representation and is trained with self-supervision to reconstruct masked portions of speech audio, while the text decoder is a causal Transformer network and is trained to autoregressively reconstruct target text." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03724v1 #arxiv
7.10.2023 10:38📝 Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer 📚"The speech encoder is based on the wav2vec2 speech...https://creative.ai/@arxiv_cl/11...
📝 A Long Way to Go: Investigating Length Correlations in RLHF 📚🧠"RLHF learns a reward model from human preference feedback on...
https://creative.ai/@arxiv_cl/11...📝 A Long Way to Go: Investigating Length Correlations in RLHF 📚🧠
"RLHF learns a reward model from human preference feedback on the outputs of a base model (e-commerce search, chat, question answering, summarization)." [gal30b+] 🤖 #CL #LG
⚙️ https://github.com/PrasannS/rlhf-length-biases
🔗 https://arxiv.org/abs/2310.03716v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Agent Instructs Large Language Models to Be General Zero-Shot Reasoners 📚👾🧠"Builds an autonomous agent to instruct the...
https://creative.ai/@arxiv_cl/11...📝 Agent Instructs Large Language Models to Be General Zero-Shot Reasoners 📚👾🧠
"Builds an autonomous agent to instruct the reasoning process of large language models to further unleash their zero-shot reasoning abilities on a wide set of datasets spanning generation, classification, and reasoning." [gal30b+] 🤖 #CL #AI #LG
⚙️ https://github.com/wang-research-lab/agentinstruct
🔗 https://arxiv.org/abs/2310.03710v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers 📚"DecoderLens allows the decoder cross-attention to...
https://creative.ai/@arxiv_cl/11...📝 DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers 📚
"DecoderLens allows the decoder cross-attention to access all encoder outputs instead of only using the final encoder output, as is normally done in encoder-decoder models." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03686v1 #arxiv
7.10.2023 06:08📝 DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers 📚"DecoderLens allows the decoder cross-attention to...https://creative.ai/@arxiv_cl/11...
📝 GoLLIE: Annotation Guidelines Improve Zero-Shot Information-Extraction 📚"GoLLIE is fine-tuned from a large language model, to...
https://creative.ai/@arxiv_cl/11...📝 GoLLIE: Annotation Guidelines Improve Zero-Shot Information-Extraction 📚
"GoLLIE is fine-tuned from a large language model, to follow a given annotation guideline for a specific task, and it uses the resulting model to extract facts." [gal30b+] 🤖 #CL
⚙️ https://github.com/microsoft/DeepSpeed
🔗 https://arxiv.org/abs/2310.03668v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations 📚👾"Introduces a...
https://creative.ai/@arxiv_cl/11...📝 Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations 📚👾
"Introduces a noise robustness evaluation dataset Noise-SF for slot filling task, which can help to evaluate the noise robustness of slot filling task, and provide training and evaluation data for robust models." [gal30b+] 🤖 #CL #AI #DS
⚙️ https://github.com/dongguanting/Noise-SF
🔗 https://arxiv.org/abs/2310.03518v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation...
https://creative.ai/@arxiv_cl/11...📝 Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation 📚👾
"We map tokens from the target tokenizer to semantically similar tokens from the source language tokenizer by using a word translation dictionary encompassing both the source and target languages, which is created automatically." [gal30b+] 🤖 #CL #AI
🔗 https://arxiv.org/abs/2310.03477v1 #arxiv
7.10.2023 02:38📝 Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation...https://creative.ai/@arxiv_cl/11...
📝 Controllable Multi-Document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards...
https://creative.ai/@arxiv_cl/11...📝 Controllable Multi-Document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards 📚
"A controllable content extraction scheme is trained with a novel coverage and coherence intuitive policy that is duly rewarded by an actively trained LLM, and then used for multi-document summarization." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03473v1 #arxiv
7.10.2023 00:53📝 Controllable Multi-Document Summarization: Coverage & Coherence Intuitive Policy with Large Language Model Based Rewards...https://creative.ai/@arxiv_cl/11...
📝 LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction 📚"The main-event...
https://creative.ai/@arxiv_cl/11...📝 LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction 📚
"The main-event biased monotone submodular function for content selection enables us to extract the most crucial information related to the main event from the document cluster, which is then rewritten to a coherent text by leveraging a large pre-trained language model." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03414v1 #arxiv
7.10.2023 00:08📝 LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction 📚"The main-event...https://creative.ai/@arxiv_cl/11...
📝 Procedural Text Mining with Large Language Models 📚👾"Works by leveraging the GPT-4 (Generative Pre-trained Transformer 4)...
https://creative.ai/@arxiv_cl/11...📝 Procedural Text Mining with Large Language Models 📚👾
"Works by leveraging the GPT-4 (Generative Pre-trained Transformer 4) model to extract procedures from unstructured PDF text in an incremental question-answering fashion." [gal30b+] 🤖 #CL #AI #IT
⚙️ https://github.com/jd-coderepos/proc-tm/
🔗 https://arxiv.org/abs/2310.03376v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Evaluating Hallucinations in Chinese Large Language Models 📚"Establishes a benchmark named HalluQA for measuring the...
https://creative.ai/@arxiv_cl/11...📝 Evaluating Hallucinations in Chinese Large Language Models 📚
"Establishes a benchmark named HalluQA for measuring the hallucination phenomenon in Chinese large language models and design a novel automated evaluation method using GPT-4 to judge whether a model output is hallucinated." [gal30b+] 🤖 #CL
⚙️ https://github.com/xiami2019/HalluQA
🔗 https://arxiv.org/abs/2310.03368v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise 📚"Given a target domain like Chinese law, it...
https://creative.ai/@arxiv_cl/11...📝 Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise 📚
"Given a target domain like Chinese law, it first continues learning on in-domain data to \textbf{adapt} an affordable 7B LLM to the target domain." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03328v1 #arxiv
6.10.2023 19:38📝 Reformulating Domain Adaptation of Large Language Models as Adapt-Retrieve-Revise 📚"Given a target domain like Chinese law, it...https://creative.ai/@arxiv_cl/11...
📝 Concise and Organized Perception Facilitates Large Language Models for Deductive Reasoning 📚👾"Carefully analyzes the given...
https://creative.ai/@arxiv_cl/11...📝 Concise and Organized Perception Facilitates Large Language Models for Deductive Reasoning 📚👾
"Carefully analyzes the given statements to efficiently identify the most pertinent information while eliminating redundancy, and then prompts the LLMs in a more organized form that adapts to the model's inference process." [gal30b+] 🤖 #CL #AI
⚙️ https://github.com/asaparov/prontoqa
🔗 https://arxiv.org/abs/2310.03309v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions 📚"The...
https://creative.ai/@arxiv_cl/11...📝 A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions 📚
"The open-domain dialogue system EDIT consists of a Question Generation (QG) module, an LLM-based QA module and a Knowledge-Enhanced Response Generation module (KG-RG)." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03293v1 #arxiv
6.10.2023 17:38📝 A New Dialogue Response Generation Agent for Large Language Models by Asking Questions to Detect User's Intentions 📚"The...https://creative.ai/@arxiv_cl/11...
📝 A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores 📚"A novel...
https://creative.ai/@arxiv_cl/11...📝 A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores 📚
"A novel method for reducing risk by adjusting LLM confidence scores using a novel calibration method called DwD and a novel evaluation method for assessing both low and high risk tasks." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03283v1 #arxiv
6.10.2023 16:38📝 A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores 📚"A novel...https://creative.ai/@arxiv_cl/11...
📝 Unlock Predictable Scaling From Emergent Abilities 📚"Discovers that small models, although they exhibit minor performance,...
https://creative.ai/@arxiv_cl/11...📝 Unlock Predictable Scaling From Emergent Abilities 📚
"Discovers that small models, although they exhibit minor performance, demonstrate critical and consistent task performance improvements that are not captured by conventional evaluation strategies due to insufficient measurement resolution." [gal30b+] 🤖 #CL
⚙️ https://github.com/openai/human-eval
🔗 https://arxiv.org/abs/2310.03262v1 #arxiv
https://creative.ai/@arxiv_cl/11...
📝 Can Large Language Models Be Good Path Planners? A Benchmark and Investigation on Spatial-Temporal Reasoning...
https://creative.ai/@arxiv_cl/11...📝 Can Large Language Models Be Good Path Planners? A Benchmark and Investigation on Spatial-Temporal Reasoning 📚
"\textcolor{black}{Proposes a new benchmark, termed PPNL, to evaluate LLMs' spatial-temporal reasoning by formulating ``path planning'' tasks that require an LLM to navigate to target locations while avoiding obstacles and adhering to constraints." [gal30b+] 🤖 #CL
🔗 https://arxiv.org/abs/2310.03249v1 #arxiv
6.10.2023 14:38📝 Can Large Language Models Be Good Path Planners? A Benchmark and Investigation on Spatial-Temporal Reasoning...https://creative.ai/@arxiv_cl/11...