Papers with output generation
Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing? (2026.eacl-srw)
Copied to clipboard
| Challenge: | Using Neural Machine Translation, we examine whether the algorithms used in NMT have inherent inductive biases that are beneficial for most types of inputs but might harm the processing of untypical texts. |
| Approach: | They propose to use a set of measures to quantify text diversity based on its statistical properties to determine whether NMT systems struggle with maintaining the diversity of such texts. |
| Outcome: | The proposed approaches maintain the diversity and complexity of language and allow for better global planning of the output generation. |
Personalized Abstractive Summarization by Tri-agent Generation Pipeline (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing research shows that large language models do not consistently satisfy users' preferences or expectations. |
| Approach: | They propose a tri-agent generation pipeline that includes a generator, an instructor, and an editor to enhance output personalization. |
| Outcome: | The proposed pipeline generates outputs that better meet user expectations on two abstractive summarization datasets. |
Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking (2023.findings-eacl)
Copied to clipboard
| Challenge: | Prompt-based methods with large pre-trained language models have shown impressive unaided performance across many NLP tasks. |
| Approach: | They propose a meta-learning scheme to stabilize the ability of the model to perform well under various prompts and introduce a saliency model to limit dialogue text length. |
| Outcome: | The proposed model improves on large pre-trained language models with labeled in-context exemplars and can be used to generate more exemplar queries. |
DSCD: Large Language Model Detoxification with Self-Constrained Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for decoding large language models (LLMs) are based on external constraints and require additional resource overhead and loss of generation fluency. |
| Approach: | They propose a method for LLMs detoxification without parameter fine-tuning that strengthens the inner token distribution while weakening that of hallucination and toxic layer during output generation. |
| Outcome: | Extensive experiments on open-source LLMs and public datasets demonstrate DSCD's state-of-the-art (SOTA) performance in detoxification and generation fluency, with superior efficiency compared to existing methods. |
Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have explored multiple aspects that affect the performance of large language models (LLMs) such as input-output mapping, extensive data resources, and the ability to train on labeled examples. |
| Approach: | They propose a framework that injects knowledge into LLMs during continual self-supervised pre-training and judiciously selects examples with high knowledge relevance. |
| Outcome: | The proposed framework outperforms baseline models and improves by more than 13% and 7% on text classification and question-answering tasks. |
How Chain-of-Thought Works? Tracing Information Flow from Decoding, Projection, and Activation (2026.findings-acl)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) prompting significantly enhances model reasoning, yet its internal mechanisms remain poorly understood. |
| Approach: | They reversely traced information flow across decoding, projection, and activation phases and found that CoT may serve as a decoding space pruner . |
| Outcome: | The proposed framework can be used to design more efficient and robust prompts. |
VisualCoder: Guiding Large Language Models in Code Execution with Fine-grained Multimodal Chain-of-Thought Reasoning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to enhance large language models' ability to predict program behavior struggle with dynamic reasoning tasks. |
| Approach: | They propose a visual control flow graph that integrates CoT reasoning with a control flow . they aim to improve performance in program behavior prediction, error detection and output generation . |
| Outcome: | The proposed approach improves program behavior prediction, error detection, and output generation. |
IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune . |
| Approach: | They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction. |
| Outcome: | The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting. |
To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to inference-time alignment are expensive and only offer guidances during output generation. |
| Approach: | They propose an inference-time alignment framework that shifts from binary decisions to creating hybrid distributions integrating both models’ knowledge. |
| Outcome: | The proposed framework reduces the number of inference-time alignment interventions and improves performance on challenging model pairs. |
Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions (2025.emnlp-main)
Copied to clipboard
| Challenge: | reducing the size of LLMs through post-training pruning has been studied, but its impact on model fairness remains unexplored. |
| Approach: | They propose a pruning method that removes parameters that are redundant for input processing but influential in output generation. |
| Outcome: | The proposed pruning method can maintain or improve fairness across models and tasks where existing methods have limitations. |
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation (2026.findings-acl)
Copied to clipboard
Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu
| Challenge: | Multimodal Large Language Models (MLLMs) are increasingly being deployed as content moderators . however, they exploit the Human-AI capability gap and create adversarial environments . smuggling attacks exploit the human-AI gap and exploit the vulnerability . |
| Approach: | They construct a benchmark to evaluate the vulnerability of MLLMs as content moderators . they identify three root causes: limited capabilities of vision encoders, robustness gap in OCR . |
| Outcome: | The proposed model exploits the Human-AI capability gap and is vulnerable to smuggling attacks. |