arXiv research

InvestLM is a financial domain LLM tuned on LLaMA-65B for investment advice.

RCPO uses ranked choice modeling for better LLM alignment.

Study reveals LLM personality patterns but lacks behavioral consistency.

Study compares DSPy teleprompter algorithms for aligning LLM evaluations with human annotations.

SAGE enhances reinforcement learning by injecting hints to prevent model stagnation.

Survey of alignment techniques for large language models.

SPPO optimizes language model alignment by treating preferences as a game and achieving state-of-the-art performance.

Method constructs finance LLMs without instruction data using pretraining and model merging.

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learnin…

Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must learn to generate programs for diverse scenes conditioned on a given symbolic instruction. Final goals are specified to our agent via images o…

Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agent's learning through trial-and-error. For instance, following natural language instructions on the Web (such as booking a flight ticket) leads to RL settings where input vocabulary and number of…

Interactive learning with hindsight instruction feedback achieves better performance than traditional methods.

In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions. We ground the meaning of instruction signals in the task-learning process, and use them simultaneously for guiding the latter. We implement our framework as a modular …

A method to improve LLMs by automating the construction of a mixture of expert prompts.

Improved financial sentiment analysis using simple instruction tuning of LLMs.

Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may foster instructing, conditioning or structuring interactive agent behavior, it remains an open-problem to correctly relate language underst…

Improves matrix multiplication throughput for asymmetric bit-width operands.

Framework improves clinical timeline reconstruction from text and tables.

Improved investment performance with fine-grained LLM tasks.

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

RAG-IT automates financial analysis using LLMs and specialized datasets.

Study finds flipped classrooms improve student self-concept, enjoyment, but not exam scores.

Study shows model size inversely affects few-shot instruction accuracy.

We solve a key problem in cross-lingual learning using a novel approach.

Enhances LLMs for predicting stock movements by considering news dissemination and context.

New method for RLHF reduces costs by integrating new data in one pass.

Improved robot navigation using multi-head attention for natural language instructions.

Emergent misalignment is influenced by training dynamics, model priors, and data.

This paper benchmarks FinGPT for financial datasets using open-source large language models.

LLMs struggle with zero-shot annotation tasks due to model-internalized priors.

This paper proposes a new method to connect language and physical actions in reinforcement learning.

LLM Pro Finance Suite enhances financial NLP with instruction-tuned models.

SymNoise improves language model fine-tuning by 6.7% over NEFTune, using symmetric noise.

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning is how to leverage multiple views to learn better representations. This is further complicated by the existence of a latent alignment between views, such as between speech a…

FinRLlama wins FinRL Challenge 2024 by fine-tuning LLMs with market data.

Predicting the number of clock cycles a processor takes to execute a block of assembly instructions in steady state (the throughput) is important for both compiler designers and performance engineers. Building an analytical model to do so is especially complicated in modern x86-64 Complex Instruction Set Computer (CISC…

Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. We propose a…

SRPO improves AI alignment with human preferences through self-improvement and task-independent optimization.

Neuro-symbolic agent learns systematic generalisation from formal instructions.

Framework learns useful subgoals from demonstrations and instructions.

Simple adaptive attacks can jailbreak state-of-the-art safety-aligned language models.

New RL framework learns task completion without prior knowledge.

WebGUM learns web navigation from multimodal data, outperforming previous methods.

Training-free looped transformers improve model performance without additional training.

Training models to prefer certain responses can unintentionally shift probability to harmful ones.

Efficient FPGA virtualization for deep learning reduces user isolation and overhead.

In2Core selects a coreset for efficient LLM fine-tuning with reduced data.

Qwen3-8B outperforms classical models in financial text classification.