TechcraftingAI NLP brings you daily summaries of the latest arXiv Computation and Language research.
TechcraftingAI NLP
Claim This Podcastby Brad Edwards
271 episodes
Updated Weekly
Accepts GuestsHas Sponsors
Podcast Overview
TechcraftingAI NLP brings you daily summaries of the latest arXiv Computation and Language research.
Language
🇺🇲
Publishing Since
9/28/2023
1 verified contact email on file for TechcraftingAI NLP
Pitch yourself as a guest, propose sponsorships, or reach out directly to the host.
Recent Episodes
June 15, 2024
Ep. 263 - Part 2 - June 13, 2024
<p>ArXiv NLP research for Thursday, June 13, 2024.</p> <p><br></p> <p>00:20: Chain-of-Though (CoT) prompting strategies for medical error detection and correction</p> <p>01:31: CoastTerm: a Corpus for Multidisciplinary Term Extraction in Coastal Scientific Literature</p> <p>02:52: RH-SQL: Refined Schema and Hardness Prompt for Text-to-SQL</p> <p>04:01: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs</p> <p>05:24: Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models</p> <p>06:38: Investigating the translation capabilities of Large Language Models trained on parallel data only</p> <p>07:56: LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks</p> <p>09:09: DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation</p> <p>11:20: Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning</p> <p>12:46: Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations</p> <p>13:53: Language Complexity and Speech Recognition Accuracy: Orthographic Complexity Hurts, Phonological Complexity Doesn't</p> <p>14:47: ReadCtrl: Personalizing text generation with readability-controlled instruction learning</p> <p>16:32: Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models</p> <p>17:49: Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs</p> <p>19:18: End-to-end Streaming model for Low-Latency Speech Anonymization</p> <p>20:22: Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback</p> <p>22:25: On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models</p> <p>23:33: Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models</p> <p>24:35: Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech</p> <p>25:47: AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models</p> <p>27:15: Transformers meet Neural Algorithmic Reasoners</p> <p>28:32: REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space</p> <p>30:02: Learning from Natural Language Explanations for Generalizable Entity Matching</p> <p>31:14: ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models</p> <p>32:29: DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding</p> <p>33:43: Improving Autoregressive Training with Dynamic Oracles</p>
June 15, 2024
Ep. 263 - Part 1 - June 13, 2024
<p>ArXiv NLP research for Thursday, June 13, 2024.</p> <p><br></p> <p>00:20: Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning</p> <p>01:53: Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models</p> <p>03:26: Automated Essay Scoring Using Grammatical Variety and Errors with Multi-Task Learning and Item Response Theory</p> <p>04:33: Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination</p> <p>06:05: DisfluencySpeech -- Single-Speaker Conversational Speech Dataset with Paralanguage</p> <p>07:26: Research on Optimization of Natural Language Processing Model Based on Multimodal Deep Learning</p> <p>08:41: ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions</p> <p>10:07: An Approach to Build Zero-Shot Slot-Filling System for Industry-Grade Conversational Assistants</p> <p>11:42: Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentation</p> <p>12:42: No perspective, no perception!! Perspective-aware Healthcare Answer Summarization</p> <p>14:28: Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models</p> <p>16:02: An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios</p> <p>17:21: Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors</p> <p>18:48: Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning</p> <p>19:52: Word Order in English-Japanese Simultaneous Interpretation: Analyses and Evaluation using Chunk-wise Monotonic Translation</p> <p>21:12: Multi-Agent Software Development through Cross-Team Collaboration</p> <p>22:55: LLM Reading Tea Leaves: Automatically Evaluating Topic Models with Large Language Models</p> <p>24:14: Bayesian Statistical Modeling with Predictors from LLMs</p> <p>25:39: ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models</p> <p>27:28: Language Models are Crossword Solvers</p> <p>28:32: MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning</p> <p>29:51: CUDRT: Benchmarking the Detection of Human vs. Large Language Models Generated Texts</p> <p>31:29: Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?</p> <p>32:59: 3M: Multi-modal Multi-task Multi-teacher Learning for Game Event Detection</p> <p>34:08: Modeling Comparative Logical Relation with Contrastive Learning for Text Generation</p> <p>35:42: SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models</p>
June 13, 2024
Ep. 262 - June 12, 2024
<p>ArXiv NLP research for Wednesday, June 12, 2024.</p> <p><br></p> <p>00:19: VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment</p> <p>02:05: BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domain</p> <p>03:15: Designing a Dashboard for Transparency and Control of Conversational AI</p> <p>04:46: Label-aware Hard Negative Sampling Strategies with Momentum Contrastive Learning for Implicit Hate Speech Detection</p> <p>05:51: Exploring Speech Foundation Models for Speaker Diarization in Child-Adult Dyadic Interactions</p> <p>06:53: Exploring Self-Supervised Multi-view Contrastive Learning for Speech Emotion Recognition with Limited Annotations</p> <p>07:52: Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation</p> <p>08:55: DeTriever: Decoder-representation-based Retriever for Improving NL2SQL In-Context Learning</p> <p>10:20: Automated Information Extraction from Thyroid Operation Narrative: A Comparative Study of GPT-4 and Fine-tuned KoELECTRA</p> <p>11:35: Large Language Model Unlearning via Embedding-Corrupted Prompts</p> <p>13:17: Defining and Detecting Vulnerability in Human Evaluation Guidelines: A Preliminary Study Towards Reliable NLG Evaluation</p> <p>14:46: Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling</p> <p>16:02: LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning</p> <p>17:18: Guiding In-Context Learning of LLMs through Quality Estimation for Machine Translation</p> <p>18:37: It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF</p> <p>20:02: Adversarial Evasion Attack Efficiency against Large Language Models</p> <p>21:06: Learning Job Title Representation from Job Description Aggregation Network</p> <p>21:59: Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey</p> <p>23:35: AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection</p> <p>24:38: Languages Transferred Within the Encoder: On Representation Transfer in Zero-Shot Multilingual Translation</p> <p>25:56: Multimodal Table Understanding</p> <p>27:20: CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems</p> <p>28:51: Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling</p> <p>30:36: Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets</p> <p>31:57: Semi-Supervised Spoken Language Glossification</p> <p>33:16: Underneath the Numbers: Quantitative and Qualitative Gender Fairness in LLMs for Depression Prediction</p> <p>34:37: A Dialogue Game for Eliciting Balanced Collaboration</p> <p>35:23: Transformer-based Model for ASR N-Best Rescoring and Rewriting</p> <p>36:16: SumHiS: Extractive Summarization Exploiting Hidden Structure</p> <p>36:53: Figuratively Speaking: Authorship Attribution via Multi-Task Figurative Language Modeling</p> <p>38:08: Leveraging Large Language Models for Web Scraping</p> <p>39:51: M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation</p> <p>41:15: Is Programming by Example solved by LLMs?</p> <p>42:29: Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques</p> <p>43:42: Towards Unsupervised Speech Recognition Without Pronunciation Models</p> <p>44:50: cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers</p> <p>45:57: Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models</p> <p>47:02: Tailoring Generative AI Chatbots for Multiethnic Communities in Disaster Preparedness Communication: Extending the CASA Paradigm</p> <p>48:12: Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL</p> <p>49:56: TasTe: Teaching Large Language Models to Translate through Self-Reflection</p> <p>51:28: OLMES: A Standard for Language Model Evaluations</p> <p>52:47: Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing</p>
271 total episodes available
Similar Podcasts
Discover related shows you might enjoy
Deep-dive analytics for TechcraftingAI NLP
Frequently asked questions
Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.
- What is TechcraftingAI NLP?
- How often does this podcast release new episodes?
This podcast updates weekly.
- Where can I listen to this podcast?
This podcast is available on 6 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
- Does this podcast accept guests?
Yes, this podcast regularly features guests.
Legal Disclaimer
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.