Search Results for author: Shibo Hao

Found 12 papers, 10 papers with code

LLM Pretraining with Continuous Concepts

no code implementations12 Feb 2025 Jihoon Tack, Jack Lanchantin, Jane Yu, Andrew Cohen, Ilia Kulikov, Janice Lan, Shibo Hao, Yuandong Tian, Jason Weston, Xian Li

We propose Continuous Concept Mixing (CoCoMix), a novel pretraining framework that combines discrete next token prediction with continuous concepts.

Knowledge Distillation Language Modeling +3

Linear Correlation in LM's Compositional Generalization and Hallucination

1 code implementation6 Feb 2025 Letian Peng, Chenyang An, Shibo Hao, chengyu dong, Jingbo Shang

The generalization of language models (LMs) is undergoing active debates, contrasting their potential for general intelligence with their struggles with basic knowledge composition (e. g., reverse/transition curse).

Hallucination

Offline Reinforcement Learning for LLM Multi-Step Reasoning

2 code implementations20 Dec 2024 Huaijie Wang, Shibo Hao, Hanze Dong, Shenao Zhang, Yilin Bao, Ziran Yang, Yi Wu

While Direct Preference Optimization (DPO) has shown promise in aligning LLMs with human preferences, it is less suitable for multi-step reasoning tasks because (1) DPO relies on paired preference data, which is not readily available for multi-step reasoning tasks, and (2) it treats all tokens uniformly, making it ineffective for credit assignment in multi-step reasoning tasks, which often come with sparse reward.

GSM8K Math +5

Training Large Language Models to Reason in a Continuous Latent Space

1 code implementation9 Dec 2024 Shibo Hao, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, Yuandong Tian

For example, most word tokens are primarily for textual coherence and not essential for reasoning, while some critical tokens require complex planning and pose huge challenges to LLMs.

Logical Reasoning

Pandora: Towards General World Model with Natural Language Actions and Video States

no code implementations12 Jun 2024 Jiannan Xiang, Guangyi Liu, Yi Gu, Qiyue Gao, Yuting Ning, Yuheng Zha, Zeyu Feng, Tianhua Tao, Shibo Hao, Yemin Shi, Zhengzhong Liu, Eric P. Xing, Zhiting Hu

This paper makes a step towards building a general world model by introducing Pandora, a hybrid autoregressive-diffusion model that simulates world states by generating videos and allows real-time control with free-text actions.

Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples

1 code implementation9 Jun 2024 Fangxu Yu, Lai Jiang, Haoqiang Kang, Shibo Hao, Lianhui Qin

To fill this gap, we propose Flow of Reasoning (FoR), an efficient diversity-seeking LLM finetuning method aimed at improving reasoning quality and diversity with minimal data.

ARC Diversity +5

LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models

1 code implementation8 Apr 2024 Shibo Hao, Yi Gu, Haotian Luo, Tianyang Liu, Xiyan Shao, Xinyuan Wang, Shuhua Xie, Haodi Ma, Adithya Samavedhi, Qiyue Gao, Zhen Wang, Zhiting Hu

(2) We develop LLM Reasoners, a library for standardized modular implementation of existing and new reasoning algorithms, under a unified formulation of the search, reward, and world model components.

BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models

2 code implementations28 Jun 2022 Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric P. Xing, Zhiting Hu

The resulting KGs as a symbolic interpretation of the source LMs also reveal new insights into the LMs' knowledge capacities.

Knowledge Graphs

Cannot find the paper you are looking for? You can Submit a new open access paper.