244 citations · 1.3k across the 96 of their papers we have counts for
9 papers · 2 filters
Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit
Hoang Pham, Duc Anh Vu, Duy Tung Doan +2
In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train…
Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments
Hoang Pham, Cong-Duy Nguyen, Dong Le +2
Persistent textual memory lets language-model agents reuse lessons from past tasks to improve on future multi-step tasks without retraining. Systems such as ACE and Dynamic Cheatsh…
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen +3
Probe-based uncertainty estimation (UE) has emerged as a prominent approach to detect hallucinations in Large Language Models (LLMs) by learning uncertainty from internal model sig…
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Jundong Xu, Qingchuan Li, Jiaying Wu +11
Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deploymen…
GRACE: Step-Level Benchmark for Faithful Reasoning over Context
Hoang Pham, Dong Le, Anh Tuan Luu
Many reasoning tasks require models to reason over input context, from document-grounded question answering to rule-based deduction. Chain-of-Thought (CoT) prompting produces trace…
Don't Read Everything: A Curvature-Conditioned Query for Linear Attention
Dong Le, Thong Nguyen, Cong-Duy Nguyen +1
Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tas…
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
Khoi Le, Tri Cao, Phong Nguyen +5
Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore,…
Learning Uncertainty from Sequential Internal Dispersion in Large Language Models
Ponhvoan Srey, Xiaobao Wu, Cong-Duy Nguyen +1
Uncertainty estimation is a promising approach to detect hallucinations in large language models (LLMs). Recent approaches commonly depend on model internal states to estimate unce…
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…