Publications
All listed papers. Full record also on Google Scholar.
-
Single LLM Debate, MoLaCE: Mixture of Latent Concept Experts Against Confirmation Bias
Preprint
Introduces MoLaCE, an inference-time method that mixes latent-concept experts so a single LLM can resist confirmation bias—emulating multi-agent debate more efficiently and reducing echo-chamber effects.
-
Measuring what Matters: Construct Validity in Large Language Model Benchmarks
NeurIPS 2025 Datasets & Benchmarks
A systematic review of 445 LLM benchmarks with 29 experts, showing how weak construct validity undermines claims about safety and capability, and offering eight recommendations for more rigorous evaluation.
-
Detecting LLM Hallucination through Layer-wise Information Deficiency
EMNLP 2025
Detects hallucinations at test time by tracking usable-information deficiencies across model layers—especially under ambiguous or unanswerable prompts—without extra training or architecture changes.
-
How Ambiguous Are the Rationales For Natural Language Reasoning?
COLING 2025
Studies how uncertain or ambiguous rationales affect reasoning performance, and proposes a simple way for models to choose among reasoning paths when rationale quality is inconsistent.
-
ATHENA: Mathematical Reasoning with Thought Expansion
EMNLP 2023
Presents ATHENA, an attention-based architecture that expands candidate mathematical thoughts step by step, improving math-word-problem solving under limited or varied training signals.
-
ALP: Data Augmentation Using Lexicalized PCFGs for Few-Shot Text Classification
AAAI 2022
Generates syntactically diverse, label-preserving text with lexicalized PCFGs for few-shot classification, and pairs this with augmentation-aware train/validation splitting for stronger low-resource training.
-
LST: Lexicon-Guided Self-Training for Few-Shot Text Classification
Arxiv
Improves few-shot self-training by guiding pseudo-labels with a refined lexicon, reducing overconfident early errors when only a handful of labeled examples are available.
