24 citations · 109 across the 40 of their papers we have counts for
10 papers · 1 filter
Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics
Jian Gu, Hongyu Zhang, Chunyang Chen +1
The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream. Between them, exist…
Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models
Jian Gu, Hongyu Zhang, Chunyang Chen +1
Code language models must be maintained like the software around them: when a library evolves, a model keeps writing the interface that it saw during training. Repairing the model…
Requirements-Augmented Generation for Trustworthy Acceptance Testing of LLM-Based Software
Fanyu Wang, Chetan Arora, Zhenping Xie +4
LLM-based software (LBS) integrates large language models as core components to deliver flexible, personalised responses. Unlike traditional software with deterministic outputs, LB…
SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models
Jian Gu, Aldeida Aleti, Chunyang Chen +1
Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anc…
CodeChat-Eval: Evaluating Large Language Models in Multi-Turn Code Refinement Dialogues
Guoxiang Guo, Kla Tantithamthavorn, Neelofar Neelofar +2
Large Language Models (LLMs) are increasingly used in software engineering to generate and refine code. In practice, developers often continue from an initial code generation reque…
ViBR: Automated Bug Replay from Video-based Reports using Vision-Language Models
Sidong Feng, Dingbang Wang, Nikola Tomic +3
Bug reports play a critical role in software maintenance by helping users convey encountered issues to developers. Recently, GUI screen capture videos have gained popularity as a b…