6 citations · 23 across the 11 of their papers we have counts for
9 papers · 1 filter
Can LLM Graph Reasoning Generalize beyond Pattern Memorization?
Yizhuo Zhang, Heng Wang, Shangbin Feng +4
Large language models (LLMs) demonstrate great potential for problems with implicit graphical structures, while recent works seek to enhance the graph reasoning capabilities of LLM…
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers
Kabir Ahuja, Vidhisha Balachandran, Madhur Panwar +4
Transformers trained on natural language data have been shown to learn its hierarchical structure and generalize to sentences with unseen syntactic structures without explicitly en…
Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks
Yichen Wang, Shangbin Feng, Abe Bohan Hou +5
The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress tes…
k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text
Abe Bohan Hou, Jingyu Zhang, Yichen Wang +2
Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection. While token-level watermarks are vulnerable to pa…
On the Zero-Shot Generalization of Machine-Generated Text Detectors
Xiao Pu, Jingyu Zhang, Xiaochuang Han +2
The rampant proliferation of large language models, fluent enough to generate text indistinguishable from human-written language, gives unprecedented importance to the detection of…
KGQuiz: Evaluating the Generalization of Encoded Knowledge in Large Language Models
Yuyang Bai, Shangbin Feng, Vidhisha Balachandran +4
Large language models (LLMs) demonstrate remarkable performance on knowledge-intensive tasks, suggesting that real-world knowledge is encoded in their model parameters. However, be…
SemStamp: A Semantic Watermark with Paraphrastic Robustness for Text Generation
Abe Bohan Hou, Jingyu Zhang, Tianxing He +7
Existing watermarking algorithms are vulnerable to paraphrase attacks because of their token-level design. To address this issue, we propose SemStamp, a robust sentence-level seman…
Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models
Wenxuan Ding, Shangbin Feng, Yuhan Liu +4
We propose Knowledge Crosswords, a geometric knowledge reasoning benchmark consisting of incomplete knowledge networks bounded by structured factual constraints, where LLMs are tas…
Resolving Knowledge Conflicts in Large Language Models
Yike Wang, Shangbin Feng, Heng Wang +4
Large language models (LLMs) often encounter knowledge conflicts, scenarios where discrepancy arises between the internal parametric knowledge of LLMs and non-parametric informatio…