Tootfinder

Algorithmic Tradeoffs, Applied NLP, and the State-of-the-Art Fallacy
AJ Alvero, Ruohong Dong, Klint Kanopka, David Lang
https://arxiv.org/abs/2509.08199 https://

Algorithmic Tradeoffs, Applied NLP, and the State-of-the-Art Fallacy
Computational sociology is growing in popularity, yet the analytic tools employed differ widely in power, transparency, and interpretability. In computer science, methods gain popularity after surpassing benchmarks of predictive accuracy, becoming the "state of the art." Computer scientists favor novelty and innovation for different reasons, but prioritizing technical prestige over methodological fit could unintentionally limit the scope of sociological inquiry. To illustrate, we focus on compu…

Too Helpful, Too Harmless, Too Honest or Just Right?
Gautam Siddharth Kashyap, Mark Dras, Usman Naseem
https://arxiv.org/abs/2509.08486 https://arxiv.org/p…

Too Helpful, Too Harmless, Too Honest or Just Right?
Large Language Models (LLMs) exhibit strong performance across a wide range of NLP tasks, yet aligning their outputs with the principles of Helpfulness, Harmlessness, and Honesty (HHH) remains a persistent challenge. Existing methods often optimize for individual alignment dimensions in isolation, leading to trade-offs and inconsistent behavior. While Mixture-of-Experts (MoE) architectures offer modularity, they suffer from poorly calibrated routing, limiting their effectiveness in alignment ta…

:range_de_chin_shite_oven_de_bun_suru:

Combining Knowledge Graphs and NLP to Analyze Instant Messaging Data in Criminal Investigations
Riccardo Pozzi, Valentina Barbera, Renzo Alva Principe, Davide Giardini, Riccardo Rubini, Matteo Palmonari
https://arxiv.org/abs/2509.26487

Combining Knowledge Graphs and NLP to Analyze Instant Messaging Data in Criminal Investigations
Criminal investigations often involve the analysis of messages exchanged through instant messaging apps such as WhatsApp, which can be an extremely effort-consuming task. Our approach integrates knowledge graphs and NLP models to support this analysis by semantically enriching data collected from suspects' mobile phones, and help prosecutors and investigators search into the data and get valuable insights. Our semantic enrichment process involves extracting message data and modeling it using a …

Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
Shrestha Ghosh, Luca Giordano, Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski
https://arxiv.org/abs/2510.07024

Mining the Mind: What 100M Beliefs Reveal About Frontier LLM Knowledge
LLMs are remarkable artifacts that have revolutionized a range of NLP and AI tasks. A significant contributor is their factual knowledge, which, to date, remains poorly understood, and is usually analyzed from biased samples. In this paper, we take a deep tour into the factual knowledge (or beliefs) of a frontier LLM, based on GPTKB v1.5 (Hu et al., 2025a), a recursively elicited set of 100 million beliefs of one of the strongest currently available frontier LLMs, GPT-4.1. We find that the mode…

Predicting the Order of Upcoming Tokens Improves Language Modeling
Zayd M. K. Zuhri, Erland Hilman Fuadi, Alham Fikri Aji
https://arxiv.org/abs/2508.19228 https://

Predicting the Order of Upcoming Tokens Improves Language Modeling
Multi-Token Prediction (MTP) has been proposed as an auxiliary objective to improve next-token prediction (NTP) in language model training but shows inconsistent improvements, underperforming in standard NLP benchmarks. We argue that MTP's exact future token prediction is too difficult as an auxiliary loss. Instead, we propose Token Order Prediction (TOP), which trains models to order upcoming tokens by their proximity using a learning-to-rank loss. TOP requires only a single additional unembed…

NLP Methods for Detecting Novel LLM Jailbreaks and Keyword Analysis with BERT
John Hawkins, Aditya Pramar, Rodney Beard, Rohitash Chandra
https://arxiv.org/abs/2510.01644 https:…

NLP Methods for Detecting Novel LLM Jailbreaks and Keyword Analysis with BERT
Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into circumventing the safety guardrails put in place to keep responses acceptable to the developer's policies. In this study, we analyse the ability of different machine learning models to distinguish jailbreak prompts from genuine uses, including looking at our abi…

🇺🇦 #NowPlaying on #BBC6Music's #AmyLamé
St. Vincent:
🎵 Pay Your Way In Pain
#StVincent
https://stvincent.bandcamp.com/track/pay-your-way-in-pain-idles-remix
https://open.spotify.com/track/1nLaoWVhNRZ38irY0LZjL6

On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey
Meishan Zhang, Xin Zhang, Xinping Zhao, Shouzheng Huang, Baotian Hu, Min Zhang
https://arxiv.org/abs/2507.20783

On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey
Text embeddings have attracted growing interest due to their effectiveness across a wide range of natural language processing (NLP) tasks, such as retrieval, classification, clustering, bitext mining, and summarization. With the emergence of pretrained language models (PLMs), general-purpose text embeddings (GPTE) have gained significant traction for their ability to produce rich, transferable representations. The general architecture of GPTE typically leverages PLMs to derive dense text repres…

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Hinrich Sch\"utze, Volker Tresp, Yunpu Ma
https://arxiv.org/abs/2508.19828

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of NLP tasks, but they remain fundamentally stateless, constrained by limited context windows that hinder long-horizon reasoning. Recent efforts to address this limitation often augment LLMs with an external memory bank, yet most existing pipelines are static and heuristic-driven, lacking any learned mechanism for deciding what to store, update, or retrieve. We present Memory-R1, a reinforcement learning …