17 papers
Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering
Zeyong Zhang, Tung Sum Thomas Kwok, Tengfei Ma +1
When a large language model solves a mathematical problem, its reasoning is largely hierarchical, and the solution often branches at a few tokens where the next-token entropy is hi…
FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering
Xinyu Wang, Tung Sum Thomas Kwok, Zhenghan Tai +1
Large language model agents increasingly answer financial questions by searching regulatory filings. Such questions are often deceptively under-specified: Meta Platforms' "operatin…
Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow
Tung Sum Thomas Kwok, Yidong Ouyang, Yingjia Wan +3
Uniform discrete flow permits repeated updates at every generation position. While continued revision supports correction of wrong tokens, it also exposes correct intermediate pred…
FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
Yanzhang Ma, Zhenghan Tai, Hanwei Wu +25
Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafter. In pr…
FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering
Jijun Chi, Zhenghan Tai, Hanwei Wu +21
Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardi…
REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
Xiaofeng Lin, Yingxu Wang, Tung Sum Thomas Kwok +4
Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind, espe…
From Table to Cell: Attention for Better Reasoning with TABALIGN
Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang +6
Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner to a left-to-…
MedFabric: Gold Evidence Hides the Difficulty of Word-Level Medical Fabrication Detection
Tung Sum Thomas Kwok, Qian Qian, Xiaofeng Lin +8
Large language models fabricate in medicine, producing fluent statements that are factually wrong, so reliable fabrication detection is a prerequisite for clinical deployment. Repo…
TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering
Tung Sum Thomas Kwok, Xinyu Wang, Xiaofeng Lin +7
Multimodal reasoning has emerged as a powerful framework for enhancing reasoning capabilities of reasoning models. While multi-turn table reasoning methods have improved reasoning…
Co-Evolution of Policy and Internal Reward for Language Agents
Xinyu Wang, Hanwei Wu, Jingwei Song +8
Large language model (LLM) agents learn by interacting with environments, but long-horizon training remains fundamentally bottlenecked by sparse and delayed rewards. Existing metho…
Enhancing Table Reasoning with Deterministic Table-State Rewards
Tung Sum Thomas Kwok, Xinyu Wang, Hengzhi He +9
Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for intermediate reasoning states. Ex…
: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers
Xinyu Wang, Hanwei Wu, Qingchen Hu +13
Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and…
VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering
Zhenghan Tai, Hanwei Wu, Qingchen Hu +24
Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from…
Towards High Supervised Learning Utility Training Data Generation: Data Pruning and Column Reordering
Tung Sum Thomas Kwok, Zeyong Zhang, Chi-Hua Wang +1
Tabular data synthesis for supervised learning ('SL') model training is gaining popularity in industries such as healthcare, finance, and retail. Despite the progress made in tabul…
FinSage: A Multi-aspect RAG System for Financial Filings Question Answering
Xinyu Wang, Jijun Chi, Zhenghan Tai +13
Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be fo…
GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction
Tung Sum Thomas Kwok, Chi-Hua Wang, Guang Cheng
Tabular data synthesis involves not only multi-table synthesis but also generating multi-modal data (e.g., strings and categories), which enables diverse knowledge synthesis. Howev…
DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room
Tung Sum Thomas Kwok, Chi-hua Wang, Guang Cheng
Data collaboration via Data Clean Room offers value but raises privacy concerns, which can be addressed through synthetic data and multi-table synthesizers. Common multi-table synt…