Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct successfully use code as LLM agents' action, achieving good results. However, CodeAct greedily generates the next action's code block by relying on fragmented thoughts, resulting in inconsistency and instability. Moreover, CodeAct lacks action-related ground-truth (GT), making its supervision signals and termination conditions questionable in multi-turn interactions. To address these issues, we first introduce a simple yet effective end-to-end code generation paradigm, CodeProgram, which leverages code's systematic logic to align with global reasoning and enable cohesive problem-solving. Then, we propose Tree-of-Code (ToC), which self-grows CodeProgram nodes based on the executable nature of the code and enables self-supervision in a GT-free scenario. Experimental results on two datasets using ten popular zero-shot LLMs show ToC remarkably boosts accuracy by nearly 20% over CodeAct with less than 1/4 turns. Several LLMs even perform better on one-turn CodeProgram than on multi-turn CodeAct. To further investigate the trade-off between efficacy and efficiency, we test different ToC tree sizes and exploration mechanisms. We also highlight the potential of ToC's end-to-end data generation for supervised and reinforced fine-tuning.

Language models have gained significant interest due to their general-purpose capabilities, which appear to emerge as models are scaled to increasingly larger parameter sizes. However, these large models impose stringent requirements on computing systems, necessitating significant memory and processing requirements for inference. This makes performing inference on mobile and edge devices challenging, often requiring invocating remotely-hosted models via network calls. Remote inference, in turn, introduces issues like latency, unreliable network connectivity, and privacy concerns. To address these challenges, we explored the possibility of deviating from the trend of increasing model size. Instead, we hypothesize that much smaller models (~30-120M parameters) can outperform their larger counterparts for specific tasks by carefully curating the data used for pre-training and fine-tuning. We investigate this within the context of deploying edge-device models to support sensing applications. We trained several foundational models through a systematic study and found that small models can run locally on edge devices, achieving high token rates and accuracy. Based on these findings, we developed a framework that allows users to train foundational models tailored to their specific applications and deploy them at the edge.

We argue that the Declarative Self-improving Python (DSPy) optimizers are a way to align the large language model (LLM) prompts and their evaluations to the human annotations. We present a comparative analysis of five teleprompter algorithms, namely, Cooperative Prompt Optimization (COPRO), Multi-Stage Instruction Prompt Optimization (MIPRO), BootstrapFewShot, BootstrapFewShot with Optuna, and K-Nearest Neighbor Few Shot, within the DSPy framework with respect to their ability to align with human evaluations. As a concrete example, we focus on optimizing the prompt to align hallucination detection (using LLM as a judge) to human annotated ground truth labels for a publicly available benchmark dataset. Our experiments demonstrate that optimized prompts can outperform various benchmark methods to detect hallucination, and certain telemprompters outperform the others in at least these experiments.

There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it correlates with accuracy. Confidence is measured (i) qualitatively in terms of persistence in keeping their answer when prompted to reconsider, and (ii) quantitatively in terms of self-reported confidence score. We investigate the performance of three LLMs -- GPT4o, GPT4-turbo and Mistral -- on two benchmark sets of questions on causal judgement and formal fallacies and a set of probability and statistical puzzles and paradoxes. Although the LLMs show significantly better performance than random guessing, there is a wide variability in their tendency to change their initial answers. There is a positive correlation between qualitative confidence and accuracy, but the overall accuracy for the second answer is often worse than for the first answer. There is a strong tendency to overstate the self-reported confidence score. Confidence is only partially explained by the underlying token-level probability. The material effects of prompting on qualitative confidence and the strong tendency for overconfidence indicate that current LLMs do not have any internally coherent sense of confidence.

Can Large Language Models (LLMs) accurately predict election outcomes? While LLMs have demonstrated impressive performance in healthcare, legal analysis, and creative applications, their capabilities in election forecasting remain uncertain. Notably, election prediction poses unique challenges: limited voter-level data, evolving political contexts, and the complexity of modeling human behavior. In the first part of this paper, we explore and introduce a multi-step reasoning framework for election prediction, which systematically integrates demographic, ideological, and time-sensitive factors. Validated on 2016 and 2020 real-world data and extensive synthetic personas, our approach adapts to changing political landscapes, reducing bias and significantly improving predictive accuracy. We further apply our pipeline to the 2024 U.S. presidential election, illustrating its ability to generalize beyond observed historical data. Beyond enhancing accuracy, the second part of the paper provides insights into the broader implications of LLM-based election forecasting. We identify potential political biases embedded in pretrained corpora, examine how demographic patterns can become exaggerated, and suggest strategies for mitigating these issues. Together, this project, a large-scale LLM empirical study, advances the accuracy of election predictions and establishes directions for more balanced, transparent, and context-aware modeling in political science research and practice.

Large language models (LLMs) have made significant advancements across various tasks, but their safety alignment remain a major concern. Exploring jailbreak prompts can expose LLMs' vulnerabilities and guide efforts to secure them. Existing methods primarily design sophisticated instructions for the LLM to follow, or rely on multiple iterations, which could hinder the performance and efficiency of jailbreaks. In this work, we propose a novel jailbreak paradigm, Simple Assistive Task Linkage (SATA), which can effectively circumvent LLM safeguards and elicit harmful responses. Specifically, SATA first masks harmful keywords within a malicious query to generate a relatively benign query containing one or multiple [MASK] special tokens. It then employs a simple assistive task such as a masked language model task or an element lookup by position task to encode the semantics of the masked keywords. Finally, SATA links the assistive task with the masked query to jointly perform the jailbreak. Extensive experiments show that SATA achieves state-of-the-art performance and outperforms baselines by a large margin. Specifically, on AdvBench dataset, with mask language model (MLM) assistive task, SATA achieves an overall attack success rate (ASR) of 85% and harmful score (HS) of 4.57, and with element lookup by position (ELP) assistive task, SATA attains an overall ASR of 76% and HS of 4.43.

Conflict scholars have used rule-based approaches to extract information about political violence from news reports and texts. Recent Natural Language Processing developments move beyond rigid rule-based approaches. We review our recent ConfliBERT language model (Hu et al. 2022) to process political and violence related texts. The model can be used to extract actor and action classifications from texts about political conflict. When fine-tuned, results show that ConfliBERT has superior performance in accuracy, precision and recall over other large language models (LLM) like Google's Gemma 2 (9B), Meta's Llama 3.1 (7B), and Alibaba's Qwen 2.5 (14B) within its relevant domains. It is also hundreds of times faster than these more generalist LLMs. These results are illustrated using texts from the BBC, re3d, and the Global Terrorism Dataset (GTD).

ChatGPT is now available on WhatsApp. Starting today, if you add 1 (800) CHAT-GPT to your contacts -- that's 1 (800) 242-8478 -- you can start using the chatbot over Meta's messaging app. In this iteration, ChatGPT is limited to text-only input, so there's no Advanced Voice Mode or visual input on offer, but you still get all the smarts of the o1-mini model. What's more, over WhatsApp ChatGPT is available everywhere OpenAI offers its chatbot, with no account necessary. OpenAI is working on a way to authenticate existing users over WhatApp, though the company did not share a timeline for when that feature might launch.

Raj Goyle, CEO of intelligence firm Bodhala and former Democratic Kansas state representative, told Fox News Digital it is encouraging to see members of both parties come together to try and determine the source of these drones. SpaceX and Tesla founder Elon Musk speaks during an America PAC town hall on October 26, 2024, in Lancaster, Pennsylvania. AI WARS: OpenAI is pushing back against Elon Musk's latest attempt to rework his lawsuit against the artificial intelligence giant that seeks to prevent the company from moving to a for-profit structure, noting in a blog post and legal filing that Musk had argued for it to do so years ago. AGE OF AI: OpenAI CEO Sam Altman is joining the list of U.S. tech titans donating to President-elect Trump's inaugural fund, a spokesperson exclusively told Fox News Digital. ARTIFICIAL INTELLIGENCE: The House task force on artificial intelligence is urging the U.S. government to aim for "a flexible sectoral regulatory framework" for the technology in a nearly 300-page report released Tuesday morning.

Neowin reports that tech giant Microsoft will be shaking up the user interface of its Microsoft 365 app early next year. In addition, the app will be getting a new icon and a small name change, henceforth to be called "Microsoft 365 Copilot" starting mid-January 2025. The app will no longer have a top header. Instead, tools like user profile, settings, and feedback will move to the bottom left toolbar. The feedback button will be available under the "Settings and more" section in the bottom left toolbar.