4 citations · 16 across the 34 of their papers we have counts for
14 papers · 1 filter
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
Xu Ouyang, Tao Ge, Thomas Hartvigsen +3
We reveal that low-bit quantization favors undertrained large language models (LLMs) by observing that models with larger sizes or fewer training tokens experience less quantizatio…
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Xiyao Wang, Linfeng Song, Ye Tian +5
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to dis…
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
Murong Yue, Wenlin Yao, Haitao Mi +3
Enhancing the capability of large language models (LLMs) in reasoning has gained significant attention in recent years. Previous studies have demonstrated the effectiveness of vari…
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
Wenlin Yao, Haitao Mi, Dong Yu
Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still lim…
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
Dian Yu, Baolin Peng, Ye Tian +3
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-sour…
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
Yuheng Zhang, Dian Yu, Baolin Peng +6
Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-b…
LiteSearch: Efficacious Tree Search for LLM
Ante Wang, Linfeng Song, Ye Tian +5
Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they of…
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Souvik Das, Lifeng Jin, Linfeng Song +3
Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Rece…
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
Ye Tian, Baolin Peng, Linfeng Song +4
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Recent work p…
Self-Consistency Boosts Calibration for Math Reasoning
Ante Wang, Linfeng Song, Ye Tian +5
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development. We design three off-the-shelf calibration methods based on s…
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation
Xiangci Li, Linfeng Song, Lifeng Jin +3
Knowledge-based, open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. Many types and sources of knowledge have previou…
Collaborative decoding of critical tokens for boosting factuality of large language models
Lifeng Jin, Baolin Peng, Linfeng Song +3
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained mod…
Fine-Grained Self-Endorsement Improves Factuality and Reasoning
Ante Wang, Linfeng Song, Baolin Peng +5
This work studies improving large language model (LLM) generations at inference time by mitigating fact-conflicting hallucinations. Particularly, we propose a self-endorsement fram…
Inconsistent dialogue responses and how to recover from them
Mian Zhang, Lifeng Jin, Linfeng Song +2
One critical issue for chat systems is to stay consistent about preferences, opinions, beliefs and facts of itself, which has been shown a difficult problem. In this work, we study…