Search Results for author:
Found 27 papers, 20 papers with code
Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning
For dialogue summarization, the subdomain of text summarization, utterances are concatenated to flat text before being processed.
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
We then compare sequential and parallel scaling strategies on QwQ, R1 and LIMO, finding that parallel scaling achieves better coverage and scalability.
Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework
To reduce human bias and enable fine-grained analysis of error patterns, we propose a novel framework for automated dynamic error classification in mathematical reasoning.
VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
General-purposed embodied agents are designed to understand the users' natural instructions or intentions and act precisely to complete universal tasks.
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability. OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining.
Unified Active Retrieval for Retrieval Augmented Generation
Experiments on four representative types of user instructions show that UAR significantly outperforms existing work on the retrieval timing judgement and the performance of downstream tasks, which shows the effectiveness of UAR and its helpfulness to downstream tasks.
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models
Recent advancements in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks.
A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond
Building on our examination of the developmental trajectories, we further investigate the emerging synergies between code intelligence and broader machine intelligence, uncovering new cross-domain opportunities and illustrating the substantial influence of code intelligence across various domains.
Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem
This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP).
Are LLMs Rational Investors? A Study on Detecting and Reducing the Financial Bias in LLMs
Results show varying degrees of financial irrationality among models, influenced by their design and training.
Turn Waste into Worth: Rectifying Top-$k$ Router of MoE
To address the dropped tokens and padding, we propose the Rectify-Router, comprising the Intra-GPU Rectification and the Fill-in Rectification.
Can AI Assistants Know What They Don't Know?
To answer this question, we construct a model-specific "I don't know" (Idk) dataset for an assistant, which contains its known and unknown questions, based on existing open-domain question answering datasets.
Pixel-level Semantic Correspondence through Layout-aware Representation Learning and Multi-scale Matching Integration
Establishing precise semantic correspondence across object instances in different images is a fundamental and challenging task in computer vision.
A Survey of Reasoning with Foundation Models
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation.
Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication
Large Language Models (LLMs) have recently made significant strides in complex reasoning tasks through the Chain-of-Thought technique.
LLatrieval: LLM-Verified Retrieval for Verifiable Generation
Thus, the LLM can iteratively provide feedback to retrieval and facilitate the retrieval result to fully support verifiable generation.
$R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
While current tasks of converting natural language to SQL (NL2SQL) using Foundation Models have shown impressive achievements, adapting these approaches for converting natural language to Graph Query Language (NL2GQL) encounters hurdles due to the distinct nature of GQL compared to SQL, alongside the diverse forms of GQL.
Evaluating Hallucinations in Chinese Large Language Models
We analyze the primary types of hallucinations in different types of models and their causes.
Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration
Large Language Models (LLMs) are evolving at an unprecedented pace and have exhibited considerable capability in the realm of natural language processing (NLP) with world knowledge.
The Rise and Potential of Large Language Model Based Agents: A Survey
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
Do Large Language Models Know What They Don't Know?
Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks.
Correspondence Transformers With Asymmetric Feature Learning and Matching Flow Super-Resolution
The asymmetric feature learning module exploits a biased cross-attention mechanism to encode token features of source images with their target counterparts.
Rethinking Label Smoothing on Multi-hop Question Answering
Multi-Hop Question Answering (MHQA) is a significant area in question answering, requiring multiple reasoning components, including document retrieval, supporting sentence prediction, and answer span extraction.
A Unified Generative Framework based on Prompt Learning for Various Information Extraction Tasks
In this paper, we propose a novel composable prompt-based generative framework, which could be applied to a wide range of tasks in the field of Information Extraction.
What Dense Graph Do You Need for Self-Attention?
Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities.
TURNER: The Uncertainty-based Retrieval Framework for Chinese NER
Chinese NER is a difficult undertaking due to the ambiguity of Chinese characters and the absence of word boundaries.
