Papers by Tong Xiang

18 papers
ALRPHFS: Adversarially Learned Risk Patterns with Hierarchical Fast & Slow Reasoning for Robust Agent Defense (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing safety checks fail to capture complex semantic risks posed by harmful user inputs or unsafe agent behaviors.
Approach: They propose a framework to bridge the semantic gap between safety checks and real-world risks.
Outcome: The proposed framework achieves superior overall performance compared to existing baselines.
Doc-React: Multi-page Heterogeneous Document Question-answering (2025.acl-short)

Copied to clipboard

Challenge: Existing methods for integrating information across multiple modalities are suboptimal for multi-page, multimodal documents.
Approach: They propose an adaptive iterative framework that balances information gain and uncertainty reduction at each step.
Outcome: The proposed framework captures relevant multimodal content and achieves strong performance on complex QA tasks.
Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in chain-of-thought prompting have demonstrated the ability of large language models to perform multi-step reasoning.
Approach: They propose a framework to analyze latent dynamics of CoT trajectories for interpretability . they segment generated CoT into discrete reasoning steps and abstract each step into a spectral embedding based on token-level Gram matrices .
Outcome: The proposed framework segments generated CoT steps into discrete reasoning steps, abstracts each step into a spectral embedding based on token-level Gram matrices, and clusters these embeddements into semantically meaningful latent states.
Are Machine Rationales (Not) Useful to Humans? Measuring and Improving Human Utility of Free-text Rationales (2023.acl-long)

Copied to clipboard

Challenge: Existing metrics like task performance of the LM generating the rationales or similarity between generated and gold rationale are not good indicators of their human utility.
Approach: They propose to use a large language model to generate rationales with better human utility by estimating its conciseness and novelty.
Outcome: The proposed model can measure human utility to a better extent by estimating its usefulness in answering similar unseen instances.
From Selection to Generation: A Survey of LLM-based Active Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been used for selection and training of data for active learning.
Approach: They propose an intuitive taxonomy that categorizes LLM-based active learning techniques and discuss the transformative roles they can play in the active learning loop.
Outcome: The proposed model can generate entirely new data instances and provide more cost-effective annotations with fewer labeled data instances.
Active Prompting with Chain-of-Thought for Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to annotate large language models rely on a fixed set of human-annotated exemplars, which are not always the most effective for different tasks.
Approach: They propose a method to adapt large language models to different tasks with task-specific example prompts (annotated with human-designed CoT reasoning) they introduce several metrics to characterize uncertainty so as to select the most uncertain questions for annotation.
Outcome: The proposed method significantly improves performance on eight complex reasoning tasks.
Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown impressive reasoning abilities when prompted with Chain-of-Thought (CoT).
Approach: They propose to categorize Chain-of-X methods by taxonomies of nodes, i.e., the X in CoX, and application tasks, and then categorise them by taxanomies and discuss potential future directions.
Outcome: The proposed methods are categorised by taxonomies of nodes, i.e., the X in CoX, and application tasks.
Plum: Prompt Learning using Metaheuristics (2024.findings-acl)

Copied to clipboard

Challenge: Recent advances in prompt learning have led to a need for general prompt optimization methods.
Approach: They propose a branch of discrete non-convex optimization methods with over 100 options as a promising approach to prompt learning.
Outcome: The proposed methods can be used to discover more human-understandable prompts that were previously unknown in reasoning and image generation tasks.
An Adaptive Prompt Generation Framework for Task-oriented Dialogue System (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing black-box large language models (LLMs) have excellent performance in task-oriented dialogue (TOD) tasks, but obtaining suitable prompts for specific tasks is challenging.
Approach: They propose a black-box large language model that generates domain and slot information in the belief state, which serves as prior knowledge for subsequent prompt generation.
Outcome: The proposed framework outperforms existing prompting methods on the MultiWOZ 2.0 dataset.
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in multimodal large language models have led to progress in tackling complex reasoning tasks that combine textual and visual information.
Approach: They introduce a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark.
Outcome: The proposed model performs lower on MMMU-Pro than on the previous benchmark, ranging from 16.8% to 26.9%.
Collaborative Policy Learning for Open Knowledge Graph Reasoning (D19-1)

Copied to clipboard

Challenge: Existing models of knowledge graph reasoning suffer from limited performance when working on sparse and incomplete graphs due to the lack of evidential paths that can reach target entities.
Approach: They propose a framework to train two collaborative agents to reason for missing facts over a graph augmented by a text corpus.
Outcome: Experiments on two public datasets show the proposed approach is effective on a knowledge graph reasoning task.
Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) can generate code from natural language queries, but runtime code generation is limited due to unverified code, security risks, longer response times, and higher computational costs.
Approach: They propose an offline simulation framework to curate a software-specific skillset by exploiting large language models and publicly available scripting guides.
Outcome: The proposed framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation.
NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Existing benchmarks on nested tool learning are lacking relevant data instances.
Approach: They propose a method to construct large-scale nested tool calls with different nesting structures using a large-quality dataset.
Outcome: The proposed method can be used to evaluate the nested tool learning abilities of large language models (LLMs) in real-world applications.
TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction (2023.findings-emnlp)

Copied to clipboard

Challenge: ChatGPT and GPT-4 are commercial large language models (LLMs) however, they may produce vague responses or incorrect answers in certain specialized domains.
Approach: They propose a token compression scheme that uses summarization and semantic compression to reduce the token size of LLMs.
Outcome: The proposed method reduces token size by doing summarization and semantic compression while reducing token size with only 1.6% accuracy drop.
CoMMIT: Coordinated Multimodal Instruction Tuning (2025.emnlp-main)

Copied to clipboard

Challenge: et al., 2024) show that multimodal instruction tuning is more effective than baselines.
Approach: They propose a multimodal balance coefficient that enables quantitative measurement of the balance of learning . they propose auxiliary regularization on the gradient to promote updating with larger step sizes .
Outcome: The proposed method is more effective than baselines in MLLM instruction tuning.
DeCoT: Debiasing Chain-of-Thought for Knowledge-Intensive Tasks in Large Language Models via Causal Intervention (2024.acl-long)

Copied to clipboard

Challenge: In large language models, external knowledge is required to augment their internal knowledge through prompts, but this does not guarantee that LLMs can identify and use relevant information in the prompts to conduct chain-of-thought reasoning.
Approach: They propose a structural causal model to formally explain the internal knowledge bias of large language models (LLMs) they review the chain-of-thought (CoT) prompting from a causal perspective and find that biased information from pretrained models can impair LLMs’ reasoning abilities.
Outcome: The proposed model enables more accurate CoT reasoning and enhances LLM generation on knowledge-intensive tasks.
Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge (2020.acl-main)

Copied to clipboard

Challenge: Chinese word segmentation and part-of-speech tagging are important fundamental tasks in natural language processing.
Approach: They propose a neural model for Chinese word segmentation and part-of-speech tagging . they incorporate context features and syntactic knowledge for each input character .
Outcome: The proposed model can learn and benefit from existing tools, but its quality may be poor.
Can Multiple-choice Questions Really Be Useful in Detecting the Abilities of LLMs? (2024.lrec-main)

Copied to clipboard

Challenge: Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) however, there are concerns about whether MCQ can truly measure LLM’s capabilities.
Approach: They propose to use multiple choice questions to evaluate large language models (LLMs) to assess their capabilities.
Outcome: The proposed methods show that MCQs are less reliable than LFGQs in terms of expected calibration error.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations