Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touché ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base; supervised DeBERTa-v3-base/large encoders; and zero-shot LLMs from 12B to 123B parameters. The results show that more context is not uniformly better: full-document context improves supervised DeBERTa encoders by 3.8-4.8 macro-F1 points over sentence-only input, but does not consistently help zero-shot LLMs. Retrieved moral knowledge is more consistently useful in matched comparisons, improving each tested model family and context condition under early fusion. However, scaling from DeBERTa-v3-base to large and from 12B to larger LLMs does not guarantee gains, and simple early fusion outperforms the tested late-fusion and cross-attention RAG variants for encoders. Per-value analyses show that context and retrieval help most for socially situated or conceptually confusable values. These findings suggest that value-sensitive NLP should evaluate context, knowledge, and model family jointly rather than treating longer inputs or larger models as universal improvements.</p>\n","updatedAt":"2026-05-22T07:14:23.827Z","author":{"_id":"660d7cc48dac0ad79a76c8ea","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/J2k1Bqwtnq1kTH5SjQyIO.jpeg","fullname":"Víctor Yeste","name":"VictorYeste","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8761616945266724},"editors":["VictorYeste"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/J2k1Bqwtnq1kTH5SjQyIO.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.22641","authors":[{"_id":"6a0fffe6a53a61ce2e422e5c","name":"Víctor Yeste","hidden":false},{"_id":"6a0fffe6a53a61ce2e422e5d","name":"Paolo Rosso","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/660d7cc48dac0ad79a76c8ea/aHJiE9UPbYopqUF91hUke.png","https://cdn-uploads.huggingface.co/production/uploads/660d7cc48dac0ad79a76c8ea/VqF7avgmu7-OPSqOxu_hO.png","https://cdn-uploads.huggingface.co/production/uploads/660d7cc48dac0ad79a76c8ea/C9ucwfTcEuiltjSth53Q2.png"],"publishedAt":"2026-05-21T00:00:00.000Z","submittedOnDailyAt":"2026-05-22T00:00:00.000Z","title":"More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts","submittedOnDailyBy":{"_id":"660d7cc48dac0ad79a76c8ea","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/J2k1Bqwtnq1kTH5SjQyIO.jpeg","isPro":false,"fullname":"Víctor Yeste","user":"VictorYeste","type":"user","name":"VictorYeste"},"summary":"Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touch{é} ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base; supervised DeBERTa-v3-base/large encoders; and zero-shot LLMs from 12B to 123B parameters. The results show that more context is not uniformly better: full-document context improves supervised DeBERTa encoders by 3.8--4.8 macro-F1 points over sentence-only input, but does not consistently help zero-shot LLMs. Retrieved moral knowledge is more consistently useful in matched comparisons, improving each tested model family and context condition under early fusion. However, scaling from DeBERTa-v3-base to large and from 12B to larger LLMs does not guarantee gains, and simple early fusion outperforms the tested late-fusion and cross-attention RAG variants for encoders. Per-value analyses show that context and retrieval help most for socially situated or conceptually confusable values. These findings suggest that value-sensitive NLP should evaluate context, knowledge, and model family jointly rather than treating longer inputs or larger models as universal improvements.","upvotes":1,"discussionId":"6a0fffe7a53a61ce2e422e5e","githubRepo":"https://github.com/VictorMYeste/human-value-detection-context-rag","githubRepoAddedBy":"user","ai_summary":"Context and moral knowledge enhance sentence-level value detection differently across model types, with full-document context benefiting supervised models but not zero-shot LLMs, and retrieved knowledge consistently improving performance through early fusion.","ai_keywords":["ValuesML","Touché ValueEval","DeBERTa-v3","zero-shot LLMs","retrieval-augmented generation","early fusion","late fusion","cross-attention","macro-F1","conceptually confusable values"],"githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6808abeaeee3b58e2eb4385e","avatarUrl":"/avatars/090100c40ac7cf9b6d371baa61ec3afc.svg","isPro":false,"fullname":"Zhangfeng Lei","user":"zhanfeng9","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.22641.md"}">
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
Abstract
Context and moral knowledge enhance sentence-level value detection differently across model types, with full-document context benefiting supervised models but not zero-shot LLMs, and retrieved knowledge consistently improving performance through early fusion.
AI-generated summary
Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touch{é} ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base; supervised DeBERTa-v3-base/large encoders; and zero-shot LLMs from 12B to 123B parameters. The results show that more context is not uniformly better: full-document context improves supervised DeBERTa encoders by 3.8--4.8 macro-F1 points over sentence-only input, but does not consistently help zero-shot LLMs. Retrieved moral knowledge is more consistently useful in matched comparisons, improving each tested model family and context condition under early fusion. However, scaling from DeBERTa-v3-base to large and from 12B to larger LLMs does not guarantee gains, and simple early fusion outperforms the tested late-fusion and cross-attention RAG variants for encoders. Per-value analyses show that context and retrieval help most for socially situated or conceptually confusable values. These findings suggest that value-sensitive NLP should evaluate context, knowledge, and model family jointly rather than treating longer inputs or larger models as universal improvements.
Community
Detecting Schwartz values in political text is difficult because implicit cues often depend on surrounding arguments and fine-grained distinctions between neighboring values. We study when context and explicit moral knowledge help sentence-level value detection. Using the ValuesML/Touché ValueEval format, we compare sentence, window, and full-document inputs; no-RAG and retrieval-augmented settings with a curated moral knowledge base; supervised DeBERTa-v3-base/large encoders; and zero-shot LLMs from 12B to 123B parameters. The results show that more context is not uniformly better: full-document context improves supervised DeBERTa encoders by 3.8-4.8 macro-F1 points over sentence-only input, but does not consistently help zero-shot LLMs. Retrieved moral knowledge is more consistently useful in matched comparisons, improving each tested model family and context condition under early fusion. However, scaling from DeBERTa-v3-base to large and from 12B to larger LLMs does not guarantee gains, and simple early fusion outperforms the tested late-fusion and cross-attention RAG variants for encoders. Per-value analyses show that context and retrieval help most for socially situated or conceptually confusable values. These findings suggest that value-sensitive NLP should evaluate context, knowledge, and model family jointly rather than treating longer inputs or larger models as universal improvements.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.22641 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.22641 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.