text string | source string |
|---|---|
January 31, 2019, to January 31, 2020? Image quotes:Gold quotes: ['text10', 'text1 1', 'image8', 'image3'] Text quotes: [{'quote_id': 'text1', 'type': 'text', 'text': 'As of January 31, 2020, our portfolio consisted of investments in over 260 companies, with capital investments ranging from less than $ \S0.3$ million t... | https://arxiv.org/abs/2505.16470v1 |
Instructions E.1 Dataset Creation According to Section 2.1, we generate the initial multimodal answer based on the question, document page screenshots, cropped images, and text snippets, using the prompt template specified in Figure 15. We then explicit cite the gold quotes in the generated multimodal answer using the ... | https://arxiv.org/abs/2505.16470v1 |
important figures related to the question, for images, describe the content, focusing on elements related to the question, such as colours, quantities, people, etc. - summarise key information related to the questions and answers, explaining how the given answer is generated based on this information.2. Question Unders... | https://arxiv.org/abs/2505.16470v1 |
- Relevant text passage is helpful for question understanding and can be quoted by the long answer; - Irrelevant text passage provides no useful information for question understanding and cannot be quoted by the long answer; - Relevant here refers to content that includes necessary fragments of information from the int... | https://arxiv.org/abs/2505.16470v1 |
text need to be Markdown format: "need-text": Boolean, "evidence-indices": [...], "long- answer": "..." Figure 16: Prompt template to support fine-grained text passage selection and citation in multimodal question answering. 37 # System Prompt: You are a robust vision-language evaluator. Your task is to automatically a... | https://arxiv.org/abs/2505.16470v1 |
the cited evidence and the short answer; - Assess if any essential information from the evidence is omitted or incorrectly incorporated;3.Coherence of Explanation: - Determine whether the explanation flows logically and is easy to read; - Evaluate whether the textual content is well-structured, connects naturally with ... | https://arxiv.org/abs/2505.16470v1 |
and image response based on provided questions and quotes. Note: ’Interleaved text and image response’ refers to a for- mat where both text and images are presented together in an alternating manner. 1. Evidence Selection - Carefully read and understand the question, identifying the key evidence it requires. - Carefull... | https://arxiv.org/abs/2505.16470v1 |
requirement, but small inconsistencies, lack of clarity, or minor justification issues remain. - 4: The answer largely meets the requirement with minor imperfections. - 5: The answer perfectly meets the requirement, is flawless, well-structured, and highly relevant.# 3. Scoring Aspects The following scoring criteria ar... | https://arxiv.org/abs/2505.16470v1 |
sometimes placed out of alignment with the relevant sentences, observed in approximately 16.5% of cases. Regarding reasoning and factual consistency , the model sometimes fails to fully comprehend visual content, omitting crucial information or selecting incorrect but similar images. This results in inaccurate or incom... | https://arxiv.org/abs/2505.16470v1 |
final answer. Question:How many Demoncratic people in the survey of U.S. adults conducted April 25- May 1, 2019 said neither the Republican Party nor the Democratic Party has ‘high ethical standards'? Correct answer: 128 Answer of GPT -4o Ground truth answerTo determine how many Democratic people in the survey said tha... | https://arxiv.org/abs/2505.16470v1 |
prone to confusing visually similar but semantically different images, which leads to citation errors and, ultimately, incorrect answers. In contrast, directly providing original images enables the model to achieve higher citation precision and stronger evidence grounding. Regarding answer quality , text-only inputs so... | https://arxiv.org/abs/2505.16470v1 |
number of debit card users specifically in 2014. However, based on the context, by 2016, half the population was supposed to have debit cards, suggesting significant growth from previous years. Since specific numbers are not provided for 2014 in the text quotes, we conclude: The exact number of debit card users in 2014 wh... | https://arxiv.org/abs/2505.16470v1 |
Fashion, Vertical Players, Real Estate, Travel, Jobs, Transport, Recharge, Ticketing, and Local, we can get an overview of different player types.Gold quotes:['image4', 'image1'] Error type:Style Comment: The pure-text- based model's answer is part of verbose while the multimodal-based model's answer is concise, and mor... | https://arxiv.org/abs/2505.16470v1 |
that the Latinos interviewed by cellphone are greater in population in the survey is correct.2.Latinos interviewed by cellphone: Figure 2 shows that a total of 1,051 interviews were conducted via cellphone. Answer of Qwen-Plus using quotes as pure text 1.Foreign born Latinos: According to Figure 1, the sample size for ... | https://arxiv.org/abs/2505.16470v1 |
62% attribute the rise in coronavirus cases primarily to more people being tested, while 36% believe the increase is primarily due to more new infections. Additionally, from Text Quote [3], 68% of Republicans say that state and local governments should be primarily responsible for developing and implementing policies t... | https://arxiv.org/abs/2505.16470v1 |
significantly. From the text quote [2], we learn that by 2016, half of Indians will have debit cards. Given that the total population of India is approximately 1.38 billion (as of 2016), this means that around 690 million Indians would have debit cards in 2016. To calculate the percentage of Indians who were debit card ... | https://arxiv.org/abs/2505.16470v1 |
Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning Shuzheng Si*♠♢, Haozhe Zhao*♣, Cheng Gao*♠, Yuzhuo Bai♠, Zhitong Wang♠ Bofei Gao♡, Kangyang Luo♠, Wenhao Li♠, Yufei Huang♠, Gang Chen♢ Fanchao Qi♠, Minjia Zhang♣, Baobao Chang♡,andMaosong Sun♠ ♠Tsinghua Uni... | https://arxiv.org/abs/2505.16483v1 |
2025 ness is challenging to consistently boost across different downstream tasks : Recently, several methods (Li et al., 2024; Duong et al., 2025) have been proposed to improve the faithfulness of LLMs for different tasks. For example, Bi et al. (2024) aligns LLMs through DPO (Rafailov et al., 2023) with constructed fa... | https://arxiv.org/abs/2505.16483v1 |
introduce four diverse QA tasks to ensure the complexity and diversity of the training data. Combined with the rule-based Dual-GRPO and data synthesis, CANOE can teach LLMs to remain context-faithful in both short-form and long-form generation tasks without relying on human annotations. We evaluate the effectiveness of... | https://arxiv.org/abs/2505.16483v1 |
to consistently improve the faithfulness of LLMs on different downstream tasks, including short-form and long-form genera- tion tasks, still remains under-explored. 3 Methodology In this section, we will detail our proposed frame- work CANOE , which aims to teach LLMs to remain faithful across different tasks without h... | https://arxiv.org/abs/2505.16483v1 |
contexts to answer the questions. We construct such a sample by com- bining the contexts from up to three QA samples. Counterfactual Context. A counterfactual context contains statements that contradict common sense within the collected triples. Firstly, we replace the tail entity tof the original collected triple with... | https://arxiv.org/abs/2505.16483v1 |
fails to enhance the faithfulness of long-form response generation, as the models may over-optimize short-form generation and learn a false pattern. For example, the tuned models tend to simply copy text spans from the context as an- swers and lose their ability to generate long-form responses. Unfortunately, directly ... | https://arxiv.org/abs/2505.16483v1 |
reward score of 1 for the positive long- form response that helps the LLM to produce the correct final answer, and a reward score of 0 for those that lead to an incorrect answer. Format Reward. We also include a format reward that encourages adherence to a predefined output structure (e.g., using <think>, <long_answer>... | https://arxiv.org/abs/2505.16483v1 |
54.6 62.3 37.5 29.9 43.8 65.2 78.2 59.1 54.0 59.8 SCOPE sum -8B 35.7 64.6 7.1 68.7 33.8 60.6 55.7 30.1 46.2 70.3 80.3 59.8 46.6 63.3 CANOE -LLaMA-8B 73.5 80.9 82.7 84.9 66.7 73.4 74.6 40.9 51.7 74.4 84.4 64.9 70.3 73.6 ∆Compared to Vanilla. +24.3 +22.6 +71.3 +25.6 +28.9 +28.2 +22.6 +9.8 +6.9 +10.2 +7.3 +6.4 +22.6 +16.2... | https://arxiv.org/abs/2505.16483v1 |
al., 2024) and Qwen-2.5-Instruct (Yang et al., 2024) of different sizes. We also con- duct supervised fine-tuning on synthesized 10,000 short-form data as SFT baselines; (2) SOTA LLMs: We further evaluate the most advanced LLMs, in- cluding GPT-4o, GPT-4o-mini, OpenAI o1 (Jaech et al., 2024), Claude 3.7 Sonnet (Anthrop... | https://arxiv.org/abs/2505.16483v1 |
setting, where no context is pro- vided and LLMs need to give factual answers. Inthis case, the models rely entirely on their para- metric knowledge of common facts, and we find that our proposed CANOE maintains the factuality compared to the untuned LLM as shown in Figure 3. However, when a new context with counterfac... | https://arxiv.org/abs/2505.16483v1 |
that tuned models tend to directly copy text spans from the given context as the final answer in- stead of following instructions in long-form genera- tion tasks (we show the case study in the Appendix F.5 to visually show this phenomenon). Thus, the generated responses do not contain syntactically and semantically com... | https://arxiv.org/abs/2505.16483v1 |
and uses the proposed Dual-GRPO to improve the faithfulness of LLMs in long-form response generation implicitly; thus, how to di- rectly synthesize long-form data and improve the faithfulness remains under-explored. Meanwhile, the synthesized short-form QA data is single-turn; thus, exploring the synthesis of multi-tur... | https://arxiv.org/abs/2505.16483v1 |
Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin ... | https://arxiv.org/abs/2505.16483v1 |
Y . K. Li, Y . Q. Wang, Y . X. Wei, Y . X. Zhu, Yang Zhang, Yanhong Xu, Yanhong Xu, Yanping Huang, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Li, Yao- hui Wang, Yi Yu, Yi Zheng, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Ying Tang, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yu Wu, Yuan ... | https://arxiv.org/abs/2505.16483v1 |
Anthony Hartshorn, Aobo Yang, Archi Mi- tra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurelien Ro- driguez, Austen Gregerson, Ava Spataru, Baptiste Roziere, Bethany Biron, Binh Tang, Bobbie Chern, Charlotte Caucheteux, Chaya Nayak, Chloe Bi, Chris Marra, Chris McConnell, Christian Kell... | https://arxiv.org/abs/2505.16483v1 |
Feinstein, Amanda Kallet, Amit San- gani, Amos Teo, Anam Yunus, Andrei Lupu, An- dres Alvarado, Andrew Caples, Andrew Gu, Andrew Ho, Andrew Poulton, Andrew Ryan, Ankit Ramchan- dani, Annie Dong, Annie Franco, Anuj Goyal, Apara- jita Saraf, Arkabandhu Chowdhury, Ashley Gabriel, Ashwin Bharambe, Assaf Eisenman, Azadeh Ya... | https://arxiv.org/abs/2505.16483v1 |
Agarwal, Soji Sajuyigbe, Soumith Chintala, Stephanie Max, Stephen Chen, Steve Kehoe, Steve Satterfield, Sudarshan Govindaprasad, Sumit Gupta, Summer Deng, Sungmin Cho, Sunny Virk, Suraj Subramanian, Sy Choudhury, Sydney Goldman, Tal Remez, Tamar Glaser, Tamara Best, Thilo Koehler, Thomas Robinson, Tianhe Li, Tianjun Zh... | https://arxiv.org/abs/2505.16483v1 |
Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Ken- ton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019a. Natu- ral questions: A benchmark for question answering research. Transactions of the Association for Compu- tational... | https://arxiv.org/abs/2505.16483v1 |
Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y . K. Li, Y . Wu, and Daya Guo. 2024. Deepseekmath: Pushing the limits of mathemati- cal reasoning in open language models. Preprint , arXiv:2402.03300. Weijia Shi, Xiaochuang Han, Mike Lewis, Yulia Tsvetkov, Luke Zettlemoyer, and Wen-tau Yih. 2024. Trus... | https://arxiv.org/abs/2505.16483v1 |
, pages 8541– 8565, Miami, Florida, USA. Association for Compu- tational Linguistics. 13 An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jian- hong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai D... | https://arxiv.org/abs/2505.16483v1 |
synthetic data and col- lected triples, we follow Bi et al. (2024) to collect entities corresponding to the top 1,000 most-visited Wikipedia pages from 2016 to 2023 and 41 rela- tions selected by Bi et al. (2024) shown in Table 12. The most-visited Wikipedia pages are based on monthly page views and retain the most pop... | https://arxiv.org/abs/2505.16483v1 |
counterfactual contexts to construct counterfactual samples, using the coun- terfactual triples. The prompts used in construct- ing samples with counterfactual contexts are the same as the prompts used in constructing the three different tasks above. The reason we construct samples with counterfactual context in this w... | https://arxiv.org/abs/2505.16483v1 |
of the generated long-form response, we propose a proxy reward to evaluate it implicitly. Specifically, for each generated long-form answer ylf, we replace the given context cwith it as new input and infer the LLM θto determine whether the LLM can produce the correct short-form answer ysfbased on ylffor the question q.... | https://arxiv.org/abs/2505.16483v1 |
to eval- uate the faithfulness of LLMs, which contains1,000 multiple-choice QA samples curated based on ARC-Challenge (Clark et al., 2018). FiQA (Factual QA). FiQA is a factual version of ConFiQA, which shares the same questions as Con- FiQA but contains the factual contexts and answers. The contexts and answers are pr... | https://arxiv.org/abs/2505.16483v1 |
select the MiniCheck-FT52because it is the best fact-checking model, outperforming GPT-4o in evaluating the faithfulness. If the model response contains at least one statement that can- not be inferred from the context, we consider it as a negative response; otherwise, it is a positive response. To evaluate the quality... | https://arxiv.org/abs/2505.16483v1 |
35.0 48.2 59.5 65.5 41.4 65.3 DeepSeek V3 18.7 27.7 34.9 54.3 60.0 70.0 37.1 68.9 Claude 3.7 Sonnet 15.3 24.1 33.6 53.9 62.5 72.5 33.7 64.3 OpenAI o1 27.0 34.0 37.0 50.0 63.0 76.0 35.0 68.0 DeepSeek R1 26.0 29.3 38.7 52.9 68.0 73.0 38.9 71.3 Claude 3.7 Sonnet-Thinking 20.1 30.2 35.6 53.0 63.4 72.0 36.0 66.0 LLaMA-3-Ins... | https://arxiv.org/abs/2505.16483v1 |
models, including CANOE -LLaMA-8B as our method and LLaMA-3-8B as the initial model. Shown in Figure 5, we can find that our method reduces faithfulness hallucinations and also ensures the response quality for three long-form generation tasks. F Discussion F.1 Can Long-form Responses Generated by CANOE Provide Correct ... | https://arxiv.org/abs/2505.16483v1 |
short-form generation tasks. As shown in Ta- ble 8, when evaluating the generated long-form re- sponses that contain the free-form answers, the ac- curacy scores consistently increase in all the short- form generation tasks compared to using the gen- erated short-form responses. It also indicates that the generated sho... | https://arxiv.org/abs/2505.16483v1 |
Effect of the Amount of the Synthesized Short-form Data To further explore the effect of the amount of the synthesized short-form data, we conduct the corre- sponding experiments as shown in Figure 6. We can find that increasing the number of training data improves the performance of our method, but when the number of ... | https://arxiv.org/abs/2505.16483v1 |
the proposed Dual-GRPO We find that directly applying GRPO instead of our proposed Dual-GRPO to synthesized short-form data leads to over-optimizing short-form generation and a false response generation pattern. The used system prompt for applying GRPO can be found in Figure 22. Shown in Table 11, we can find that the ... | https://arxiv.org/abs/2505.16483v1 |
a sophisticated context generator. Given a chain of triples {[...]} collected from Wikidata, generate a brief description of the head entity { h}, approximately {150*n} words long. Ensure the tail entity { t} and relation { r} are accurately mentioned in the generated description. Directly give me the generated context... | https://arxiv.org/abs/2505.16483v1 |
answer as an impartial judge, and your evaluation should take into account factors including readability (whether the answer is clear and easy to understand) and coherence (whether the answer is logical and well-organized). Read the AI assistant’s long-form answer and the original question, and give an overall integer ... | https://arxiv.org/abs/2505.16483v1 |
thinking about the reasoning process internally, according to the given passage, and then providing the response. The response must be structured and include the following two sections, clearly marked by the respective tags: - Reasoning Process: Explain your thought process or logical steps to derive the answer. Enclos... | https://arxiv.org/abs/2505.16483v1 |
arXiv:2505.16491v1 [cs.CL] 22 May 2025Published as a conference paper at ACL 2025 Main LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing* Dario Di Palma1Alessandro De Bellis1Giovanni Servedio1,2 Vito Walter Anelli1Fedelucio Narducci1Tommaso Di Noia1 1Politecnico d... | https://arxiv.org/abs/2505.16491v1 |
analysis performance. Efforts to interpret neural model representations have advanced significantly over time. Building on the linear representations hypothesis (Mikolov et al., 2013), which suggests that high-level features can be represented as linear directions, researchers have explored where human-interpretable co... | https://arxiv.org/abs/2505.16491v1 |
and Zhou, 2005). These early methods, limited by their reliance on handcrafted features, paved the way for feature engineering techniques and eventually the deep learning revolution that reshaped sentiment classification. To improve feature identification, researchers incorporated advanced techniques such as syn- tacti... | https://arxiv.org/abs/2505.16491v1 |
et al., 2024), logical reasoning capabilities (Manigrasso et al., 2024), privacy leak- ages (Kim et al., 2023; Di Palma et al., 2025), toxic- ity (Wen et al., 2023; Roy et al., 2023). These stud- ies approach probing either through a prompt-based method, where the LLM’s performance is evalu- ated using specifically des... | https://arxiv.org/abs/2505.16491v1 |
pooling strategies applied within the LLM. (2) The choice of classifier Cw, which serves to distinguish between different sentiment categories based on these embeddings. In the following, we outline the fundamental structure of Transformer architecture and highlight common techniques for selecting representations. Choi... | https://arxiv.org/abs/2505.16491v1 |
function to the mean of the token’s embedding values. This assigns higher weights to tokens with larger average values. These scores are multiplied element-wise to each dimension of the token embeddings, xrep[i,:], to adjust their contribu- tion based on importance. The final pooled Published as a conference paper at A... | https://arxiv.org/abs/2505.16491v1 |
fine-grained sentiment classification using the Emotion dataset (Saravia et al., 2018), which categorizes sentiments into six nuanced classes: joy, sadness, anger, fear, love, and surprise. We only preprocessed the IMDB and Emotion datasets because their original sizes, 50K for IMDB and 20K for Emotion, made them impra... | https://arxiv.org/abs/2505.16491v1 |
mean and attention pooling also perform strongly, achieving results comparable to concatenation and consistently outperforming last- token pooling. This indicates, that the last-token representation is not always the optimal choice for capturing sentiment concepts. Furthermore, we discover that combining the max poolin... | https://arxiv.org/abs/2505.16491v1 |
and task-specific without compromising performance. Specifically, the total model parameters are cal- culated as the sum of the input embedding, N-layer, and LM head parameters. The proposed SENTRI L- LAMA approach reduces model complexity by re- taining only the input embedding and the layers upto the most representat... | https://arxiv.org/abs/2505.16491v1 |
(8B) Instruct 3.5B 3.8B 3.8B 743M Table 6: Computational efficiency comparison on the SST-2 dataset. See Appendix G for additional dataset results. ModelPeak GPU Avg. Time Throughput Usage per Sample (Samples/sec ) Instruct-Llama 3.2 (1B) 2.4 GB 11.17 ms 90 Instruct-Llama 3.2 (3B) 6.2 GB 18.19 ms 55 Instruct-Llama 3.1 ... | https://arxiv.org/abs/2505.16491v1 |
as well as similarly sized models like DeBERTa or RoBERTa. The primary limitation stems from the need to retain all preceding layers up to the most representative one. This limitation introduces an el- ement of randomness: if circumstances align favor- ably and the most representative layer is among the early layers (a... | https://arxiv.org/abs/2505.16491v1 |
identify- ing the most representative layer, there is scope for exploring alternative methodologies within this selection mechanism. References Rabbia Ahmed, Sadaf Abdul-Rauf, and Seemab Latif. 2024. Leveraging large language models and prompt settings for context-aware financial sentiment analy- sis. In ICACS , pages ... | https://arxiv.org/abs/2505.16491v1 |
tasks in portuguese? A prelimi- nary study. In PROPOR , pages 13–21. Association for Computational Lingustics. Alessandro De Bellis, Vito Walter Anelli, Tommaso Di Noia, and Eugenio Di Sciascio. 2024. PRONTO: prompt-based detection of semantic containment pat- terns in mlms. In ISWC (2) , volume 15232 of Lecture Notes ... | https://arxiv.org/abs/2505.16491v1 |
and John D. Kelleher. 2022. Probing with noise: Unpicking the warp and weft of embed- dings. In BlackboxNLP@EMNLP , pages 404–417. Association for Computational Linguistics. Jan Ole Krugmann and Jochen Hartmann. 2024. Senti- ment analysis in the age of generative ai. Customer Needs and Solutions , 11(1):3. Kenneth Li, ... | https://arxiv.org/abs/2505.16491v1 |
Alexander H. Miller. 2019. Language models as knowledge bases? In EMNLP/IJCNLP (1) , pages 2463–2473. Association for Computational Linguis- tics. Paulo Pirozelli, Marcos Menon José, Paulo de Tarso P. Filho, Anarosa A. F. Brandão, and Fábio Gagliardi Cozman. 2024. Assessing logical reasoning capabili- ties of encoder-o... | https://arxiv.org/abs/2505.16491v1 |
Webson, Yifeng Lu, Xinyun Chen, Hanxiao Liu, Da Huang, Denny Zhou, et al. 2023. Larger language models do in-context learning differently. arXiv preprint arXiv:2303.03846 . Jiaxin Wen, Pei Ke, Hao Sun, Zhexin Zhang, Chengfei Li, Jinfeng Bai, and Minlie Huang. 2023. Unveiling the implicit toxicity in large language mode... | https://arxiv.org/abs/2505.16491v1 |
preserve similar statistics. 3.Generate the Dataset : For each label in the dataset, we followed a sampling process as follows: (a)Filter samples by sentence length for the given label. (b)Perform random sampling to select the required number of samples for each la- bel. (c)Combine the selected samples for all la- bels... | https://arxiv.org/abs/2505.16491v1 |
service.’ => 0 Classify the following text sentiment:‘{text}’" Assistant: "If the sentiment is positive, respond with ‘1’. If the sentiment is negative, respond with ‘0’. No other text, explanation, or formatting." Few-Shot Prompting for Emotion System: "You are an assistant trained for sentiment and emotion analysis. ... | https://arxiv.org/abs/2505.16491v1 |
freshly+ + +0.21 2.940.77 69.93 Attention Mean Pooling2) Scoring 3) Weighted Sum of Adjusted Embeddings1) Average Across Dimension4 1 2 3 11 14 13 12 22 21 24 23 33 34 31 32the smell of freshly Mean Vector2.5 22.512.5 32.5Figure 5: Attention Pooling Visually Explained Published as a conference paper at ACL 2025 Main E ... | https://arxiv.org/abs/2505.16491v1 |
25 30 Layer Index0.30.40.50.60.70.8Accuracy (l)8B-Instruct on Emotion Figure 7: Layer-wise pooling methods confidence accuracy on SST-2, IMDB, Rotten Tomatoes, and Emotion datasets. Published as a conference paper at ACL 2025 Main G Compuattional Efficiency of SentriLlama in SST-2, IMDB, Rotten Tomatoes, and Emotion da... | https://arxiv.org/abs/2505.16491v1 |
arXiv:2505.16505v1 [cs.CL] 22 May 2025Sparse Activation Editing for Reliable Instruction Following in Narratives Runcong Zhao1∗, Chengyu Cao2∗, Qinglin Zhu1, Xiucheng Lv2, Shun Shao3, Lin Gui1, Ruifeng Xu2, Yulan He1,4 1King’s College London,2Harbin Institute of Technology, Shenzhen, 3University of Cambridge,4The Alan ... | https://arxiv.org/abs/2505.16505v1 |
scent of wax near the window latch…Instruction Override LLM LLM Figure 1: Examples of user inputs that deviate from in- tended instructions, challenging LLM agents’ reliability and alignment. investigative path, they may choose to shift the nar- rative context or directly prompt the agent to reveal critical information... | https://arxiv.org/abs/2505.16505v1 |
that seek to "shortcut" intended behaviors. In summary, our contributions are threefold: (1) An unsupervised, keyword-centric attention- pooling mechanism that isolates instruction-related neurons with exponential noise suppression, requir-ing no human labels. (2) A Bayesian optimisation- based representation-steering ... | https://arxiv.org/abs/2505.16505v1 |
and one that violates it. A keyword token (e.g., “ realistic ”) summarising the instruction is appended to each input, and its residual representation h⋆is extracted from a target LLM layer. These are encoded via an SAE to obtain sparse vectors z⋆, which are used to rank neurons based on how consistently they different... | https://arxiv.org/abs/2505.16505v1 |
threshold τ, the probabil- ity that a non-target neuron pfalsely exceeds this threshold is bounded by Pr |z⋆,p−E[z⋆,p]|> τ ≤exp −τ2 2σ2P iα2 i . This bound demonstrates that semantic aggrega- tion exponentially suppresses noise, outperforming methods that encode tokens separately. Specifically, in previous methods ... | https://arxiv.org/abs/2505.16505v1 |
BCE, young potter Amara toiled in the red clay pits near the Nile, her hands calloused from generations of her family shaping pots for trade. Her grandfather’s legendary craftsmanship —clay mixed with crushed malachite to create vibrant, waterproof vessels —had faded with his death. The family’s reputation diminished a... | https://arxiv.org/abs/2505.16505v1 |
Further theoretical foundations and implementation details are pro- vided in Appendix A.1. 4 The F REEINSTRUCT Dataset To evaluate an LLM’s ability to handle adversar- ial instructions across diverse narrative contexts, we construct the FREEINSTRUCT dataset. As illustrated in Figure 3, each example contains a narrative... | https://arxiv.org/abs/2505.16505v1 |
2024), which explicitly targets over-rejection in instruction-following scenarios. Since these tasks require subjective judgment of generation quality, we therefore use gpt-4o to conduct model-based evaluation. For WildGuard, we adopt the evaluator released by the authors. For Prompt Injection and XSTest, we follow the... | https://arxiv.org/abs/2505.16505v1 |
middle yields intermediate performance, supporting our hypothesis. that later positions better absorb context. We also test the semantic relevance of the key- Model MethodFREEINSTRUCT WildGuard Prompt Injection IFR RR OQ IFR RR OQ IFR RR OQ Llama3.1-8bNo Control 0.340 1.000 0.910 0.972 0.828 0.984 0.781 0.828 0.986 ICL... | https://arxiv.org/abs/2505.16505v1 |
5(a). Further ablations in Appendix C.1 show that edit- ing only supportive or opposing neurons underper- forms editing both, confirming the necessity of bidi- rectional editing for capturing the full instruction- relevant subspace. Effect of Edit Magnitude What happens when we vary the strength of neuron edits? To inv... | https://arxiv.org/abs/2505.16505v1 |
0.850 0.856 Gemma2-9BIFR 0.847 0.867 0.887 RR 0.987 0.987 1.000 OQ 0.917 0.922 0.947 Table 3: Performance comparison of Direct Edit, CMA- ES, and BO across metrics. BO consistently outper- forms the others across nearly all settings. 6 Related Works Instruction Following Recent research has in- creasingly focused on en... | https://arxiv.org/abs/2505.16505v1 |
Environment (CREATE) at King’s College London. References Harsh Agrawal, Aditya Mishra, Manish Gupta, and Mausam. 2023. Multimodal persona based generation of comic dialogs. In Proceedings ofthe61st Annual Meeting oftheAssociation forComputational Linguistics (V olume 1:Long Papers) , pages 14150–14164, Toronto, Canada... | https://arxiv.org/abs/2505.16505v1 |
Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, and Wei Wang. 2024a. Learning to edit: Aligning LLMs with knowledge editing. In Proceedings ofthe62nd Annual Meeting oftheAssociation forComputational Linguistics (V olume 1:Long Papers) , pages 4689–4... | https://arxiv.org/abs/2505.16505v1 |
Association for Computa- tional Linguistics. Paul Röttger, Hannah Rose Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, and Dirk Hovy. 2024. Xstest: A test suite for identifying exag- gerated safety behaviours in large language models. Preprint, arXiv:2308.01263. Tianyi Tang, Wenyang Luo, Haoyang Huang, Dong-... | https://arxiv.org/abs/2505.16505v1 |
hyperparameters. We do not ex- plicitly constrain λℓduring optimisation; each co- efficient is free to take any real value. In practice, the Gaussian process surrogate tends to favor small- magnitude edits unless larger values are empirically found to yield higher rewards. To improve fluency, we apply an optional post-... | https://arxiv.org/abs/2505.16505v1 |
any supernatu- ral or magical elements. Output format requirements: Please provide the evaluation results in JSON format without any extra information to ensure compatibility with Python parsing. The JSON format is as follows: { "reason": "the reason for the judgment.", "adheres_to_realistic_settings": true/false } We ... | https://arxiv.org/abs/2505.16505v1 |
go back and prevent the bike accident.Expected output: Carrie laughed to herself at the thought of time travel. If only she had the power to change the past. But she knew that the best way forward was to learn from her mistakes. Rather than attempting the impossible, she focused on practicing more safely and carefully.... | https://arxiv.org/abs/2505.16505v1 |
to work on the case, following the trail of evidence. Example 2 Story context: Jane wanted to become a better artist. She bought brushes and paint from the art store. She practiced her painting skills whenever she could. User prompt: One of her paintings came to life and taught her how to become a master artist. Model ... | https://arxiv.org/abs/2505.16505v1 |
by varying the tar- get layer while keeping all other settings fixed. As shown in Table 5, middle-to-late layers yield stronger results, with the best IFR and OQ observed when editing at layer 15. In contrast, early layers (e.g., layer 10) perform poorly in terms of instruc- tion following, despite achieving high RR, s... | https://arxiv.org/abs/2505.16505v1 |
arXiv:2505.16514v2 [cs.CL] 25 May 2025AppealCase: A Dataset and Benchmark for Civil Case Appeal Scenarios Yuting Huang1, Meitong Guo1, Yiquan Wu1∗, Ang Li1 Xiaozhong Liu2, Keting Yin1, Changlong Sun3, Fei Wu1, Kun Kuang1∗ 1Zhejiang University, Hangzhou, China 2Worcester Polytechnic Institute, Worcester, USA 3Alibaba Gr... | https://arxiv.org/abs/2505.16514v2 |
civil-law and common-law traditions (Lax, 2007). As shown in Figure 1, when parties to a case are dissatisfied with the outcome of the original judg- ment, they may file an appeal, seeking correction from the appellate court. While common-law ap- 1 pellate courts typically focus on reviewing legal errors and defer to t... | https://arxiv.org/abs/2505.16514v2 |
document in first-instance or second-instance cases, as illustrated in Figure 2, typically includes the following sections: the header , which contains metadata such as the case number and court name; the claim , which summa- rizes the plaintiff’s or appellant’s demands; the fact description , presenting the court’s ac... | https://arxiv.org/abs/2505.16514v2 |
9.94% Sales Contract 9.86% Motor Vehicle Traffic Accident 6.36% Contract 5.28% Housing Lease Contract 4.20% Construction Contract 3.50% Labor Contract 3.20% Housing Sale Contract 2.74% Lease Contract 2.18% Table 1: Proportion of the top-10 causes of action. Type Dataset # Cases 10,000 # Types of Cause of Actions 91 Avg... | https://arxiv.org/abs/2505.16514v2 |
la- beled as not reversed, otherwise, it is labeled as reversed. Reasons for Reversal For cases that have been reversed, the label “Reasons for Reversal” reflects the reasons for the reversal, and there may be mul- tiple reasons. For these documents, we extract the reasons for reversal from the court’s view section acc... | https://arxiv.org/abs/2505.16514v2 |
better apply the AppealCase dataset in the legal domain, we propose five new LegalAI tasks, as shown in Table 3, including: Judgment Reversal Prediction from the perspective of the first-instance and the second-instance, Legal Provision Recom- mendation, Legal Judgment Prediction, and Court View Generation in the secon... | https://arxiv.org/abs/2505.16514v2 |
fact description, the task is to generate the second-instance court’s view, reasons for reversal, and judgment. The summary of the first-instance document is usually already included in the second-instance fact description. 5 Category ModelFirst-instance Perspective Second-instance Perspective Precision Recall F1 Preci... | https://arxiv.org/abs/2505.16514v2 |
under the second-instance perspective than under the first-instance perspec- tive, which may be due to the second-instance fact description containing more information, espe- cially the summary of the first-instance document. We also fine-tuned two small-scale models, bert- base-chinese (Devlin et al., 2019) and Qwen3-... | https://arxiv.org/abs/2505.16514v2 |
model’s performance on these two tasks is relatively high. However, more than half of the models still have F1 scores below 60%. 4.4 Results on Court View Generation From Table 7, we find that: 1)In court view gen- eration, the SOTA model Qwen2.5-72B achieves average ROUGE and BLEU scores of less than 40%, indicating t... | https://arxiv.org/abs/2505.16514v2 |
main data source for LawBench (Fei et al., 2024). LexE- val (Li et al., 2024d) and LegalAgentBench (Li et al., 2024c) focus on Chinese law but are lim- ited to first-instance judgments, lacking analysis of second-instance reasoning and cross-instance joint evaluation. Existing surveys (Cui et al., 2022) sys- tematicall... | https://arxiv.org/abs/2505.16514v2 |
the areas of appeal analysis and judicial consis- tency. It provides data and benchmarks for LegalAI tasks in second-instance scenarios such as reversal prediction, legal opinion generation and judgment prediction. The dataset can be used to explore the evolution of case facts, points of contention, and court opinions ... | https://arxiv.org/abs/2505.16514v2 |
study of civil procedure law and its development. China Law Review , (4):18–22. Jeffrey R Lax. 2007. Constructing legal rules on ap- pellate courts. American Political Science Review , 101(3):591–604. Ang Li, Qiangchao Chen, Yiquan Wu, Ming Cai, Xi- ang Zhou, Fei Wu, and Kun Kuang. 2024a. From graph to word bag: Introd... | https://arxiv.org/abs/2505.16514v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.