Papers by Xinliang Frederick Zhang
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
Yunxiang Zhang, Muhammad Khalifa, Lechen Zhang, Xin Liu, Ayoung Lee, Xinliang Frederick Zhang, Farima Fatahi Bayat, Lu Wang
| 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
Xinliang Frederick Zhang, Anhad Mohananey, Alexandra Chronopoulou, Pinelopi Papalampidi, Somit Gupta, Tsendsuren Munkhdalai, Lu Wang, Shyam Upadhyay
| 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. |