2 citations · 2 across the 18 of their papers we have counts for
19 papers
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Yiming Huang, Ziche Liu, Zhuohang Wu +12
Scientific law discovery has long been central to scientific progress, proceeding through iterative cycles of generating hypotheses, testing them against empirical evidence, and re…
SimSD: Simple Speculative Decoding in Diffusion Language Models
Junxia Cui, Haotian Ye, Runchu Tian +9
Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decodi…
Simulating Organized Group Behavior: New Framework, Benchmark, and Analysis
Xinkai Zou, Yiming Huang, Zhuohang Wu +5
Simulating how organized groups (e.g., corporations) make decisions (e.g., responding to a competitor's move) is essential for understanding real-world dynamics and could benefit r…
How Well Does Generative Recommendation Generalize?
Yijie Ding, Zitian Guo, Jiacheng Li +8
A widely held hypothesis for why generative recommendation (GR) models outperform conventional item ID-based models is that they generalize better. However, there is few systematic…
Codified Finite-state Machines for Role-playing
Letian Peng, Yupeng Hou, Kun Zhou +1
Modeling latent character states is crucial for consistent and engaging role-playing (RP) with large language models (LLMs). Yet, existing prompting-based approaches mainly capture…
Deriving Character Logic from Storyline as Codified Decision Trees
Letian Peng, Kun Zhou, Longfei Yun +2
Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weak…
Codified Foreshadowing-Payoff Text Generation
Longfei Yun, Kun Zhou, Yupeng Hou +2
Foreshadowing and payoff are ubiquitous narrative devices through which authors introduce commitments early in a story and resolve them through concrete, observable outcomes. Howev…
A Tale of LLMs and Induced Small Proxies: Scalable Small Language Models for Knowledge Mining
Sipeng Zhang, Longfei Yun, Zilong Wang +2
At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language mode…
The Price of Format: Diversity Collapse in LLMs
Longfei Yun, Chenyang An, Zilong Wang +2
Instruction-tuned large language models (LLMs) employ structured templates, such as role markers and special tokens, to enforce format consistency during inference. However, we ide…
Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
Yuwei Zhang, Wenhao Yu, Shangbin Feng +5
Despite significant advances in large language models (LLMs), their knowledge memorization capabilities remain underexplored, due to the lack of standardized and high-quality test…
Codifying Character Logic in Role-Playing
Letian Peng, Jingbo Shang
This paper introduces Codified Profiles for role-playing, a novel approach that represents character logic as structured, executable functions for behavioral decision-making. Each…
Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting
Lizhe Zhang, Wentao Chen, Li Zhong +3
Large language models (LLMs) have recently demonstrated exceptional code generation capabilities. However, there is a growing debate whether LLMs are mostly doing memorization (i.e…
UltraGen: Extremely Fine-grained Controllable Generation via Attribute Reconstruction and Global Preference Optimization
Longfei Yun, Letian Peng, Jingbo Shang
Fine granularity is an essential requirement for controllable text generation, which has seen rapid growth with the ability of LLMs. However, existing methods focus mainly on a sma…
Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
Letian Peng, Zilong Wang, Feng Yao +1
Massive high-quality data, both pre-training raw texts and post-training annotations, have been carefully prepared to incubate advanced large language models (LLMs). In contrast, f…
Linear Correlation in LM's Compositional Generalization and Hallucination
Letian Peng, Chenyang An, Shibo Hao +2
The generalization of language models (LMs) is undergoing active debates, contrasting their potential for general intelligence with their struggles with basic knowledge composition…
Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
Letian Peng, Chenyang An, Jingbo Shang
Language model (LM) decoding is based on the next-token prediction (NTP) probability distribution. For neural LMs (e.g., Transformer-based), NTP distribution is essentially a softm…
Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification
Letian Peng, Yi Gu, Chengyu Dong +2
For extremely weak-supervised text classification, pioneer research generates pseudo labels by mining texts similar to the class names from the raw corpus, which may end up with ve…
Incubating Text Classifiers Following User Instruction with Nothing but LLM
Letian Peng, Jingbo Shang
In this paper, we aim to generate text classification data given arbitrary class definitions (i.e., user instruction), so one can train a small text classifier without any human an…
Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
Letian Peng, Jingbo Shang
Persona-driven role-playing (PRP) aims to build AI characters that can respond to user queries by faithfully sticking with all persona statements. Unfortunately, existing faithfuln…