TACL 2026 论文列表

Multimodal classifiers function as opaque black box models. While several techniques exist to interpret their predictions, very few of them are as intuitive and accessible as natural language explanations (NLEs). To build trust, such explanations must faithfully capture the classifier’s internal decision making behavior, a property known as faithfulness. In this paper, we propose CAuSE (Causal Abstraction under Simulated Explanations), a novel framework to generate faithful NLEs for any pretrained multimodal classifier. We demonstrate that CAuSE generalizes across datasets and models through extensive empirical evaluation. Theoretically, we show that CAuSE, trained via interchange intervention, forms a causal abstraction of the underlying classifier. We further validate this through a redesigned metric for measuring causal faithfulness in multimodal settings. CAuSE surpasses other methods on this metric, with qualitative analysis reinforcing its advantages. We also perform detailed error analysis to pinpoint the failure cases of CAuSE1.

We address the fundamental task of inferring cross-document coreference and hierarchy in scientific texts, which has important applications in knowledge graph construction, search, recommendation and discovery. Large Language Models (LLMs) can struggle when faced with many long-tail technical concepts with nuanced variations. We present a novel method which generates context-dependent definitions of concept mentions by retrieving full-text literature, and uses the definitions to enhance detection of cross-document relations. We further generate relational definitions, which describe how two concept mentions are related or different, and design an efficient re-ranking approach to address the combinatorial explosion involved in inferring links across papers. In both fine-tuning and in-context learning settings, we achieve large gains in performance on data subsets with high amount of different surfaces forms and ambiguity, that are challenging for models. We provide analysis of generated definitions, shedding light on the relational reasoning ability of LLMs over fine-grained scientific concepts.

Spurred by the demand for interpretable models, research on explainable AI for language technologies has experienced significant growth, with feature attribution methods emerging as a cornerstone of this progress. While prior work in NLP explored such methods for classification tasks and textual applications, explainability intersecting generation and speech is lagging, with existing techniques failing to account for the autoregressive nature of state-of-the-art models and to provide finegrained, phonetically meaningful explanations. We address this gap by introducing Spectrogram Perturbation for Explainable Speech-to-text Generation (SPES), a feature attribution technique applicable to sequence generation tasks with autoregressive models. SPES provides explanations for each predicted token based on both the input spectrogram and the previously generated tokens. Extensive evaluation on speech recognition and translation demonstrates that SPES generates explanations that are faithful and plausible to humans.

We present ZhoBLiMP, the largest linguistic minimal pair benchmark for Chinese, with over 100 paradigms, ranging from topicalization to the Ba construction. We then train from scratch a suite of Chinese language models (LMs) with different tokenizers, parameter sizes, and token volumes, to study the learning curves of LMs on Chinese. To mitigate the biases introduced by unequal lengths of the sentences in a minimal pair, we propose a new metric named sub-linear length normalized log-probabilities (SLLN-LP). Using SLLN-LP as the metric, our results show that Anaphor, Quantifiers, and Ellipsis in Chinese are difficult for LMs even up to 32B parameters, and that SLLN-LP successfully mitigates biases in ZhoBLiMP, JBLiMP and BLiMP. We conclude that future evaluations should be more carefully designed to consider the intricate relations between linking functions, LMs, and targeted minimal pairs.

Reinforcement learning (RL) has been proven to be an effective and robust method for training neural machine translation systems, especially when paired with powerful reward models that accurately assess translation quality. However, most research has focused on RL methods that use sentence-level feedback, leading to inefficient learning signals due to the reward sparsity problem—the model receives a single score for the entire sentence. To address this, we propose a novel approach that leverages fine-grained, token-level quality assessments along with error severity levels using RL methods. Specifically, we use xCOMET, a state-of-the-art quality estimation system, as our token-level reward model. We conduct experiments on small and large translation datasets with standard encoder-decoder and large language models-based machine translation systems, comparing the impact of sentence-level versus fine-grained reward signals on translation quality. Our results show that training with token-level rewards improves translation quality across language pairs over baselines according to both automatic and human evaluation. Furthermore, token-level reward optimization improves training stability, evidenced by a steady increase in mean rewards over training epochs.

Analogical reasoning is an essential aspect of human cognition. In this paper, we summarize key theories about the processes underlying analogical reasoning from the cognitive science literature and relate it to current research in natural language processing. While these processes can be easily linked to concepts in NLP, they are generally not viewed through a cognitive lens. Furthermore, we show how these notions are relevant for several major challenges in NLP research, not directly related to analogy solving. This may guide researchers to better optimize relational understanding in text, as opposed to relying heavily on entity-level similarity.

Evaluating natural language generation systems is challenging due to the diversity of valid outputs. While human evaluation is the gold standard, it suffers from inconsistencies, lack of standardization, and demographic biases, limiting reproducibility. LLM-based evaluators offer a scalable alternative but are highly sensitive to prompt design, where small variations can lead to significant discrepancies. In this work, we propose an inversion learning method that learns effective reverse mappings from model outputs back to their input instructions, enabling the automatic generation of highly effective, model-specific evaluation prompts. Our method requires only a single evaluation sample and eliminates the need for time-consuming manual prompt engineering, thereby improving both efficiency and robustness. Our work contributes toward a new direction for more robust and efficient LLM-based evaluation.

To enhance the efficiency of the attention mechanism within large language models (LLMs), previous works primarily compress the Key-Value cache or group attention heads, while largely overlooking redundancy between layers. Our comprehensive analyses across various LLMs show that highly similar attention patterns persist within most layers. It’s intuitive to reduce the redundancy by sharing attention weights across layers. However, further analysis reveals two challenges: (1) Directly sharing the weight matrix without carefully rearranging the attention heads proves to be ineffective; (2) Shallow layers are vulnerable to small deviations in attention weights. Driven by these insights, we introduce LiSA, a lightweight substitute for self-attention in well-trained LLMs. LiSA employs tiny feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights. Evaluations encompassing 13 typical benchmarks demonstrate that LiSA maintains high response quality in terms of accuracy and perplexity while reducing redundant attention calculations within 53% −84% of the total layers. Our implementations of LiSA achieve a 6 × compression of Q and K matrices within the attention mechanism, with maximum throughput improvements 19.5%, 32.3%, and 40.1% for LLaMA3-8B, LLaMA2-7B, and LLaMA2-13B, respectively. Our code is available at https://github.com/takagi97/lisa.

We present a systematic analysis of module-level design choices in GraphRAG, a retrieval-augmented generation framework that integrates structured knowledge graphs into question answering. Focusing on triple extraction, community clustering, and report generation, we evaluate multiple strategies across two knowledge-intensive benchmarks. Our results show that high-quality triple extraction is critical, as the accuracy and coverage of the resulting knowledge graph can become a bottleneck for downstream reasoning. We also find that the granularity of fundamental knowledge units, as determined by community clustering, has a significant impact on downstream performance: Achieving a balance between factual detail and topical coherence within each unit is important to enable precise and comprehensive retrieval and to facilitate effective multi-hop reasoning. In addition, simple template-based reporting outperforms LLM-based summarization in both accuracy and efficiency. These findings provide practical guidance for the structure- aware design of retrieval-augmented systems.

In people, the ability to solve analogies such as “body: feet:: table: ?” emerges in childhood, and appears to transfer easily to other domains, such as the visual domain “(: ) :: < : ?”. Recent research shows that large language models (LLMs) can solve various forms of analogies. However, can LLMs generalize analogy solving to other domains like people can? To investigate this, we had children, adults, and LLMs solve a series of letter-string analogies (e.g., a b : a c :: j k : ?) in the Latin alphabet, in a near transfer domain (Greek alphabet), and a far transfer domain (list of symbols). Children and adults easily generalized their knowledge to unfamiliar domains, whereas LLMs did not. This key difference between human and AI performance is evidence that these LLMs still struggle with robust human-like analogical transfer.

Grammatical features across human languages exhibit intriguing correlations, often attributed to learning biases in humans. Language models (LMs) provide a scalable and naturalistic framework for studying artificial language learning—one not available in human research. We investigate how learnability varies across typologically plausible and implausible languages that closely follow the word order universals identified by linguistic typologists. Our study trains LMs on highly naturalistic counterfactual versions of English (head-initial) and Japanese (head-final). Compared to prior work, our datasets more precisely target the boundary between typological plausibility and implausibility. Our experiments show that LMs learn subtly implausible languages more slowly, though they eventually reach similar performance on some metrics regardless of typological plausibility. These findings suggest that LMs exhibit typologically aligned learning preferences and that certain typological patterns may emerge from general learning biases. https://github.com/sally-xu-42/Typological_Universals.

Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation breakdown. A key issue is that current systems fail to incorporate the rich contextual information necessary to resolve ambiguities and omitted details, resulting in literal, inappropriate, or misaligned translations. In this work, we present a framework to improve large language model-based translation systems by incorporating contextual information in bilingual conversational settings during training and inference. We validate our proposed framework on two task-oriented domains: customer chat and user-assistant interaction. Across both settings, the system produced by our framework—TowerChat—consistently results in better translations than state-of-the-art systems like GPT-4o and TowerInstruct, as measured by multiple automatic translation quality metrics on several language pairs. We also show that the resulting model leverages context in an intended and interpretable way, improving consistency between the conveyed message and the generated translations.1

Current automated fact-checking (AFC) approaches typically evaluate evidence either implicitly via the predicted verdicts or through exact matches with predefined closed knowledge sources, such as Wikipedia. However, these methods are limited due to their reliance on evaluation metrics originally designed for other purposes and constraints from closed knowledge sources. In this work, we introduce Ev2R which combines the strengths of reference-based evaluation and verdict-level proxy scoring. Ev2R jointly assesses how well the evidence aligns with the gold references and how reliably it supports the verdict, addressing the shortcomings of prior methods. We evaluate Ev2R against three types of evidence evaluation approaches: reference-based, proxy-reference, and reference-less baselines. Assessments against human ratings and adversarial tests demonstrate that Ev2R consistently outperforms existing scoring approaches in accuracy and robustness. It achieves stronger correlation with human judgments and greater robustness to adversarial perturbations, establishing it as a reliable metric for evidence evaluation in AFC.1

Existing LLM-based role-playing methods often rely on superficial textual descriptions or simplistic metrics, inadequately modeling both intrinsic and extrinsic character dimensions. Additionally, they typically simulate character memory with implicit model knowledge or basic retrieval augment generation without explicit memory alignment, compromising memory consistency. The two issues weaken reliability of role-playing LLMs in several applications, such as trustworthy social simulation. To address these limitations, we propose PsyMem, a novel framework integrating fine-grained psychological attributes and explicit memory control for role-playing. PsyMem supplements textual descriptions with 26 psychological indicators to detailed model character. Additionally, PsyMem implements memory alignment training, explicitly trains the model to align character’s response with memory, thereby enabling dynamic memory-controlled responding during inference. By training Qwen2.5-7B-Instruct on our specially designed dataset (including 5,414 characters and 38,962 dialogues extracted from novels), the resulting model, termed as PsyMem-Qwen, outperforms baseline models in role-playing, achieving the best performance in human-likeness and character fidelity.

Automatic fact-checking aims to support professional fact-checkers by offering tools that can help speed up manual fact-checking. Yet, existing frameworks fail to address the key step of producing output suitable for broader dissemination to the general public: While human fact-checkers communicate their findings through fact-checking articles, automated systems typically produce little or no justification for their assessments. Here, we aim to bridge this gap. In particular, we argue for the need to extend the typical automatic fact-checking pipeline with automatic generation of full fact-checking articles. We first identify key desiderata for such articles through a series of interviews with experts from leading fact-checking organizations. We then develop Qraft, an LLM-based agentic framework that mimics the writing workflow of human fact-checkers. Finally, we assess the practical usefulness of Qraft through human evaluations with professional fact-checkers. Our evaluation shows that while Qraft outperforms several previously proposed text-generation approaches, it lags considerably behind expert-written articles. We hope that our work will enable further research in this new and important direction. The code for our implementation is available at https://github.com/mbzuai-nlp/qraft.git.

Large Language Models (LLMs) have great potential to accelerate and support scholarly peer review and are increasingly used as fully automatic review generators (ARGs). However, potential biases and systematic errors may pose significant risks to scientific integrity; understanding the specific capabilities and limitations of state-of-the-art ARGs is essential. We focus on a core reviewing skill that underpins high-quality peer review: detecting faulty research logic. This involves evaluating the internal consistency between a paper’s results, interpretations, and claims. We present a fully automated counterfactual evaluation framework that isolates and tests this skill under controlled conditions. Testing a range of ARG approaches, we find that, contrary to expectation, flaws in research logic have no significant effect on their output reviews. Based on our findings, we derive three actionable recommendations for future work and release our counterfactual dataset and evaluation framework publicly.1

Characters are important in narratives. They move the plot forward, create emotional connections, and embody the story’s themes. Visual storytelling methods focus more on the plot and events relating to it, without building the narrative around specific characters. As a result, the generated stories feel generic, with character mentions being absent, vague, or incorrect. To mitigate these issues, we introduce a new character-centric approach to visual story generation. We present the first model capable of predicting visual stories with consistently grounded and coreferent character mentions. Our model is finetuned on a new dataset which we build on top of the widely used VIST (Huang et al., 2016) benchmark. Specifically, we develop an automated pipeline to enrich VIST with visual and textual character coreference chains. We also propose new evaluation metrics to measure the richness of characters and coreference in stories. Experimental results show that our model generates stories with recurring characters which are consistent and coreferent to larger extent compared to baselines and state-of-the-art systems.1 Our code and dataset are available at https://github.com/iz2late/character-centric-vist.

Large Language Models (LLMs) excel at many tasks, yet they struggle to produce truly creative, diverse ideas. In this paper, we introduce a novel approach that enhances LLM creativity. We apply LLMs for translating between natural language and structured representations, and perform the core creative leap via cognitively inspired manipulations on these representations. Our notion of creativity goes beyond superficial token-level variations; rather, we recombine structured representations of existing ideas, enabling our system to effectively explore a more abstract landscape of ideas. We demonstrate our approach in the culinary domain with DishCover, a model that generates creative recipes. Experiments and domain-expert evaluations reveal that our outputs, which are mostly coherent and feasible, significantly surpass GPT-4o in terms of novelty and diversity, thus outperforming it in creative generation. We hope our work inspires further research into structured creativity in AI.

This paper introduces MERLIN, a novel testbed system for the task of Multilingual Multimodal Entity Linking. The created dataset includes BBC news article titles, paired with corresponding images, in five languages: Hindi, Japanese, Indonesian, Vietnamese, and Tamil, featuring over 7,000 named entity mentions linked to 2,500 unique Wikidata entities. We also include several benchmarks using multilingual and multimodal entity linking methods exploring different language models like LLaMa-2 and Aya-23. Our findings indicate that incorporating visual data improves the accuracy of entity linking, especially for entities where the textual context is ambiguous or insufficient, and particularly for models that do not have strong multilingual abilities. For the work, the dataset, methods are available online.1