9 citations · 15 across the 13 of their papers we have counts for
14 papers
Rethinking Self-Distillation for Multi-Teacher Capability Merging
Roy Xie, Dan Friedman, Feng Nan +7
Combining capabilities of multiple expert models trained starting from the same base checkpoint has become increasingly common in frontier language-model post-training. Recent tren…
SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs
Jiacheng Sang, Mengyuan Li, Sanxing Chen +3
LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible evidence is retrieved to ad…
Lazy Grounding: Attacking Search Agents with Factual Evidence
Yulin Zhang, Yukun Huang, Sanxing Chen +4
Search agents mitigate hallucination by grounding their answers in retrieved web results. However, retrieval-based approaches also introduce an attack surface: agents may cite misi…
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
Yukun Huang, Leonardo F. R. Ribeiro, Momchil Hardalov +3
Search-augmented LLM agents can produce deep research reports (DRRs), but verifying claim-level factuality remains challenging. Existing fact-checkers are primarily designed for ge…
When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
Sanxing Chen, Xiaoyin Chen, Yukun Huang +2
While Large Language Models (LLMs) hold promise to become autonomous agents, they often explore suboptimally in sequential decision-making. Recent work has sought to enhance this c…
Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models
Yukun Huang, Sanxing Chen, Jian Pei +2
Large language models can answer questions correctly and still hallucinate their citations. Most citation systems address this by retrieving documents at inference time. Retrieval…
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeoff
Maximilian Holsman, Yukun Huang, Bhuwan Dhingra
Speculative Decoding (SD) enforces strict distributional equivalence to the target model when accepting candidate tokens. While it maintains the target model's generation quality,…
To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts
Yukun Huang, Sanxing Chen, Hongyi Cai +1
Large Language Models (LLMs) are often augmented with external contexts, such as those used in retrieval-augmented generation (RAG). However, these contexts can be inaccurate or in…
Real-time Factuality Assessment from Adversarial Feedback
Sanxing Chen, Yukun Huang, Bhuwan Dhingra
We show that existing evaluations for assessing the factuality of news from conventional sources, such as claims on fact-checking websites, result in high accuracies over time for…
Atomic Self-Consistency for Better Long Form Generations
Raghuveer Thirukovalluru, Yukun Huang, Bhuwan Dhingra
Recent work has aimed to improve LLM generations by filtering out hallucinations, thereby improving the precision of the information in responses. Correctness of a long-form respon…
Calibrating Long-form Generations from Large Language Models
Yukun Huang, Yixin Liu, Raghuveer Thirukovalluru +2
To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses be…
Alexpaca: Learning Factual Clarification Question Generation Without Examples
Matthew Toles, Yukun Huang, Zhou Yu +1
Real-life tasks such as giving legal or technical advice often lack complete context at the outset and can have disparate answers depending thereon. The ability to derive missing f…
In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
Yukun Huang, Yanda Chen, Zhou Yu +1
Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from…
Learning a Better Initialization for Soft Prompts via Meta-Learning
Yukun Huang, Kun Qian, Zhou Yu
Prompt tuning (PT) is an effective approach to adapting pre-trained language models to downstream tasks. Without a good initialization, prompt tuning doesn't perform well under few…