12 citations · 60 across the 72 of their papers we have counts for
34 papers · 1 filter
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use
Junjie Ye, Yilong Wu, Sixian Li +9
Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments, a critical step toward generalized AI. However, the standard supervi…
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
Yiwen Ding, Zhiheng Xi, Wei He +7
Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effect…
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs
Xin Zhou, Ping Nie, Yiwen Guo +7
Retrieval-Augmented Generation (RAG) significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks. While existing research seeks to enhance…
Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs
Shuo Li, Tao Ji, Xiaoran Fan +10
In the study of LLMs, sycophancy represents a prevalent hallucination that poses significant challenges to these models. Specifically, LLMs often fail to adhere to original correct…
Distill Visual Chart Reasoning Ability from LLMs to MLLMs
Wei He, Zhiheng Xi, Wanxu Zhao +6
Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs), including recognizing key information from visual inputs a…
RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
Enyu Zhou, Guodong Zheng, Binghai Wang +11
Reward models (RMs) guide the alignment of large language models (LLMs), steering them toward behaviors preferred by humans. Evaluating RMs is the key to better aligning LLMs. Howe…
60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering
Junjie Ye, Yuming Yang, Qi Zhang +5
Large language models (LLMs) encode extensive world knowledge through pre-training on massive datasets, which can then be fine-tuned for the question-answering (QA) task. However,…
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data
Han Xia, Songyang Gao, Qiming Ge +3
Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Pr…
TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities
Ming Zhang, Caishuang Huang, Yilong Wu +10
Task-oriented dialogue (TOD) systems aim to efficiently handle task-oriented conversations, including information collection. How to utilize TOD accurately, efficiently and effecti…
Toward Optimal LLM Alignments Using Two-Player Games
Rui Zheng, Hongyi Guo, Zhihan Liu +10
The standard Reinforcement Learning from Human Feedback (RLHF) framework primarily focuses on optimizing the performance of large language models using pre-collected prompts. Howev…
AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
Zhiheng Xi, Yiwen Ding, Wenxiang Chen +17
Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community. Large language models (LLMs) a…
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition
Yuming Yang, Wantong Zhao, Caishuang Huang +11
Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent stu…
Length Generalization of Causal Transformers without Position Encoding
Jie Wang, Tao Ji, Yuanbin Wu +5
Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers…
MetaRM: Shifted Distributions Alignment via Meta-Learning
Shihan Dou, Yan Liu, Enyu Zhou +9
The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the tra…
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models
Wei He, Shichun Liu, Jun Zhao +6
Large language models (LLMs) have shown promising abilities of in-context learning (ICL), adapting swiftly to new tasks with only few-shot demonstrations. However, current few-shot…
LongHeads: Multi-Head Attention is Secretly a Long Context Processor
Yi Lu, Xin Zhou, Wei He +5
Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length…
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals
Rui Zheng, Yuhao Zhou, Zhiheng Xi +3
Deep neural networks (DNNs) are notoriously vulnerable to adversarial attacks that place carefully crafted perturbations on normal examples to fool DNNs. To better understand such…
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
Zhiheng Xi, Wenxiang Chen, Boyang Hong +18
In this paper, we propose R: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the bene…
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Jun Zhao, Can Zu, Hao Xu +6
Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks. However, LLMs with long context windows have…
Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution
Nuo Xu, Jun Zhao, Can Zu +9
Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preferen…
CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models
Huijie Lv, Xiao Wang, Yuansen Zhang +6
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). Thi…
RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions
Yuansen Zhang, Xiao Wang, Zhiheng Xi +4
Large Language Models (LLMs) have showcased remarkable capabilities in following human instructions. However, recent studies have raised concerns about the robustness of LLMs when…
On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe
Ningyu Xu, Qi Zhang, Menghan Zhang +2
Probing and enhancing large language models' reasoning capacity remains a crucial open question. Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capac…
LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognition
Junjie Ye, Nuo Xu, Yikun Wang +4
Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable…