Papers by Xinliang Frederick Zhang

11 papers
Identifying inherent disagreement in natural language inference (2021.naacl-main)

Copied to clipboard

Challenge: Natural language inference is the task of determining whether text is entailed, contradicted or unrelated to another piece of text.
Approach: They propose to tease systematic inferences from disagreement items by capturing modes in annotations to simulate uncertainty in the annotation process.
Outcome: The proposed approach performs statistically better than baselines on the CommitmentBank corpus in English.
MOKA: Moral Knowledge Augmentation for Moral Event Extraction (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for discerning moral values are limited due to lack of context, lack of moral reasoning capabilities and complexity of moral stances.
Approach: They propose a framework for moral event extraction using moral words and moral scenarios.
Outcome: The proposed framework outperforms baselines across three moral event understanding tasks.
Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated impressive performance in many reasoning tasks, but temporal reasoning remains challenging due to its intrinsic complexity.
Approach: They propose a new prompting technique tailored for temporal reasoning, Narrative-of-Thought (NoT), that first converts the events set to a Python class, then prompts a small model to generate a temporal narrative.
Outcome: The proposed technique achieves the highest F1 on Schema-11 evaluation set, while securing an overall F1 of par with GPT-3.5/4.
Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis (2022.emnlp-main)

Copied to clipboard

Challenge: Prior work on ideology prediction has focused on single modalities, i.e., text or images.
Approach: They propose a task where a model predicts binary or five-point scale ideological leanings given a text-image pair with political content.
Outcome: The proposed model outperforms the state-of-the-art model by almost 4% and a strong multimodal baseline with no pretraining by over 3%.
Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation (2022.emnlp-main)

Copied to clipboard

Challenge: a new task is needed to understand the interaction between entities when inferring stances.
Approach: They propose a task that primes models to identify entities in their canonical names and discern stances jointly.
Outcome: The proposed model outperforms strong comparisons by large margins.
Logit Arithmetic Elicits Long Reasoning Capabilities Without Training (2026.findings-acl)

Copied to clipboard

Challenge: Large reasoning models exhibit long chain-of-thought reasoning with complex strategies such as backtracking and self-verification, yet, these capabilities typically require resource-intensive post-training.
Approach: They propose a decoding-time approach which transfers long chain-of-thought reasoning capabilities from a substantially smaller reasoning guider to a large non-reasoning target.
Outcome: The proposed method improves performance over a model 21x smaller than the target model by 21.5% and 24.2% over the model.
COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval (2021.emnlp-main)

Copied to clipboard

Challenge: 16K FAQ items scraped from 55 credible websites . 32 human-annotated FAQ items for each query.
Approach: They present a large, challenging dataset for FAQ retrieval for COVID-19 . they use a FAQ bank, Query Bank and Relevance Set to evaluate the dataset .
Outcome: The proposed model achieves 48.8 under P@5 and is compared with other datasets.
ULTRA: Unleash LLMs’ Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement (2024.findings-acl)

Copied to clipboard

Challenge: Structural extraction of events within discourse is critical for event-centric understanding . document-level EAE focuses on arguments that are scattered across an entire document . ULTRA is a hierarchical framework that extracts event arguments more cost-effectively .
Approach: They propose a hierarchical framework that extracts event arguments more cost-effectively . ULTRA sequentially reads text chunks of a document to generate a candidate argument set . they propose to use a supervised model to find the exact boundary of an argument .
Outcome: The proposed framework outperforms strong models and ChatGPT by 9.8% when evaluated by Exact Match (EM).
Do LLMs Really Need 10+ Thoughts for “Find the Time 1000 Days Later”? Towards Structural Understanding of LLM Overthinking (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on LLMs' thought processes are limited to superficial, profiling-based observations, failing to delve into their inner workings.
Approach: They propose a utility-based definition of overthinking that moves beyond length-based metrics and provides a more insightful understanding of LLMs' thought progression.
Outcome: The proposed model decomposes the LLM thought process into minimally complete sub-thoughts and identifies common thinking patterns for topically similar queries.
PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process (2025.emnlp-main)

Copied to clipboard

Challenge: Large language model (LLM) personalization aims to align outputs with individuals’ unique preferences and opinions.
Approach: They integrate a cognitive dual-memory model into LLM personalization by mirroring episodic memory to historical user engagements and semantic memory to long-term, evolving user beliefs.
Outcome: The proposed framework integrates the well-established cognitive dual-memory model into LLM personalization, using episodic and semanticmemories.
POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection (2022.findings-naacl)

Copied to clipboard

Challenge: a lack of general-purpose tools to characterize and predict ideology across genres of text remains a challenge . a recent study compared ideology-driven pretraining tasks with long or formal written texts .
Approach: They propose to use a large-scale dataset to train pretraining models that compare political news articles on the same story written by different ideologies.
Outcome: The proposed model outperforms baseline models and state-of-the-art models on ideology prediction and stance detection tasks.

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