Related papers: EVINCE: Optimizing Multi-LLM Dialogues Using Condi…
Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…
We propose a novel LLM-based framework for reasoning in discrete, game-theoretic tasks, illustrated with \emph{Tic-Tac-Toe}. The method integrates in-context learning with entropy-guided chain-of-thought (CoT) reasoning and adaptive context…
Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents. Despite wide success of RL, training effective agents remains difficult due to the multitude of factors requiring careful tuning, such as…
We introduce the Mutual Information Machine (MIM), a probabilistic auto-encoder for learning joint distributions over observations and latent variables. MIM reflects three design principles: 1) low divergence, to encourage the encoder and…
Probabilistic reasoning systems combine different probabilistic rules and probabilistic facts to arrive at the desired probability values of consequences. In this paper we describe the MESA-algorithm (Maximum Entropy by Simulated Annealing)…
With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large quantity of retrieved knowledge to solve complex tasks. However, the limited context window…
Using results from neurobiology on perceptual decision making and value-based decision making, the problem of decision making between lotteries is reformulated in an abstract space where uncertain prospects are mapped to corresponding…
In many large language model (LLM) alignment applications, users expect not only high-quality outputs but also substantial diversity. However, existing methods often face a fundamental trade-off between these objectives: approaches that…
Vision-Language-Action (VLA) models integrate visual perception, language understanding, and action decision-making for cross-modal semantic alignment, exhibiting broad application potential. However, the joint processing of…
Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study…
Despite huge advances, LLMs still lack convenient and reliable methods to quantify the uncertainty in their responses, making them difficult to trust in high-stakes applications. One of the simplest approaches to eliciting more accurate…
Collaborative research often includes contributors with varied perspectives from diverse linguistic backgrounds. However, English as a Second Language (ESL) researchers often struggle to communicate during meetings in English and comprehend…
In recent years, large language models have shown exceptional performance in fulfilling diverse human needs. However, their training data can introduce harmful content, underscoring the necessity for robust value alignment. Mainstream…
When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…
Large language models (LLMs) have improved significantly in their reasoning through extensive training on massive datasets. However, relying solely on additional data for improvement is becoming increasingly impractical, highlighting the…
Quantifying the directionality of information flow is instrumental in understanding, and possibly controlling, the operation of many complex systems, such as transportation, social, neural, or gene-regulatory networks. The standard Transfer…
With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated single-agent architectures to multi-agent systems with…
The application of standard sufficient dimension reduction methods for reducing the dimension space of predictors without losing regression information requires inverting the covariance matrix of the predictors. This has posed a number of…
Conversational Question Simplification (CQS) aims to simplify self-contained questions into conversational ones by incorporating some conversational characteristics, e.g., anaphora and ellipsis. Existing maximum likelihood estimation (MLE)…
Vision-Language Models (VLMs) have gained community-spanning prominence due to their ability to integrate visual and textual inputs to perform complex tasks. Despite their success, the internal decision-making processes of these models…